Upcoming Seminars and Events

From bench to bedside - a fantastic voyage of drug/device development - Europe and US

Gautam Maitra, AC Immune
Hasnaà Haddouck, Swedish Orphan Biovitrum
Norma Shafer, Steadmed Mediacal
Ary Saaman, Debiotech
Claude Amman, Amman Consulting
Ajit Simh, San Diego
Matthew Scherer, FDA - Europe Office

4-week fully online course (60-70 hours in total) jointly organized by EPFL and the College of Sciences, San Diego State University. Experienced instructors from Europe and the US will introduce you to the fundamentals of drug/device development, and the requirements for regulatory and quality compliance. You will have exposure to the requirements in Europe and the US in terms of the approach, the attitude to risk-taking, and the cultural divide.

Who can participate?

  • Members of Swiss Academic Institutions with a minimum of a Bachelor degree, in a relevant field
  • Members of early Start-ups, linked to a Swiss University, may be eligible; please contact the organizer

Practical information:
  • Starts on August 30, 2021
  • 4-weeks fully online interactive course with a total of 60-70 hours, including lectures, team-work and self-study
  • Jointly organized by EPFL and the College of Sciences, San Diego State University
  • Highly experienced instructors from Europe and US, including member of FDA
  • Pricing: EPFL members 200 CHF, non-EPFL members 400 CHF
  • Limited participants, first come first served

Why should you participate?

Advances in biotechnology, medical technology, and information technology give new hope for treating diseases never imagined before. To bring these advances from the laboratory bench to the patient bedside requires training and experience that are not available in academia, this course is intended to fill that gap.

Students who successfully complete this course will be able to:
  • Describe the major steps of the drug and device development process from bench to bed-side
  • Compare and contrast US and European Union regulatory and quality requirements
  • Discuss the basics of a Quality Management System
  • Develop a Product Profile for a drug/device product or therapy
  • Draft the basic components of a Development Plan for a Phase 1 clinical trial, including a pre-clinical Plan, a Clinical Trial Protocol, and CMC (Chemistry, Manufacturing and Controls) Plan
  • Work with other life science professionals on a team
  • Feel more confident about job seeking and job interviews

Read more

GHI Floor Seminars

Xavier Pierrat - Persat lab & Mark Hanson - Lemaitre lab

The GHI Floor Seminar series covers various fields of research in Life Sciences, with an emphasis on microbiology, host-pathogen interactions, and immunology.
It features two 20-minute-talks by PhD students and post-docs (followed by a short Q&A session) as well as short talks from local professors or platform directors, and classical seminars from scientists working outside the Lausanne area.
The GHI floor seminar series is taking place on Tuesdays at 12h15, usually in room SV 1717.

COVID-19: the talks will take place in SV 1717, 30 people allowed with COVID certificate, and will be also streamed via Zoom.

If you are not a GHI member and wish to attend the seminars, please register following this link: https://epfl.zoom.us/j/64924921252?pwd=VkNteFUrVllzY0ljUWRheUZrcFg2dz09


Read more

MechE Colloquium: Deciphering Shock-Induced Amorphization in Ultrahard Ceramics

Prof. Ghatu Subhash, Laboratory for Dynamic Response of Advanced Materials (LDRAM), Mechanical and Aerospace Engineering, University of Florida

Abstract:
The hardest materials for engineering applications include diamond (HV>100 GPa), cubic-boron nitride (HV=60-75 GPa), boron carbide (HV>30 GPa), and boron suboxide (HV>40 GPa). While the former two have diamond structure with a density of 3.5 g/cm^3, the latter two have icosahedral structure with a density of 2.5 g/cm^3. These icosahedral solids exhibit high compressive strength (in excess of 5 GPa) and better thermal and chemical stability than diamond-like structures. These properties favor them in applications including protective armor, abrasives and wear resistant materials, machine tool bits, etc. However, under high-pressure deformation, such as those encountered in indentation and ballistic impact, these boron-rich solids undergo a deleterious deformation mechanism referred to as ‘amorphization’ (loss of crystalline order). Mystery has surrounded the appearance of new peaks in Raman spectrum of amorphized boron carbide (B4C), but to-date, no convincing explanation exists on its origins. This mechanism has been responsible for reduced hardness and nonrealization of the intrinsic potential of B4C. In this research, the pressure-dependent response of the amorphized B4C is investigated using experiments, microscopy, Raman spectroscopy, and molecular dynamics simulations. We propose a new rationale towards deciphering the amorphization behavior centered on atomic interactions in the amorphous islands. Quantum mechanical simulations (DFT and DFPT) are utilized to understand the stress dependence of Raman spectra, while results from molecular dynamics (MD) simulations of volumetric compression and shock loading are used to understand thermodynamic aspects of amorphization. The derived pressure-volume relationship (Hugoniot) has been found to match well with reported experimental data. The consequences of amorphization are addressed in relation to volumetric change in the nanosized amorphized islands and the stress state in the surrounding regions. Finally, new insight into quasi-longitudinal and quasi-transverse wave propagation in single crystal B4C are investigated through MD simulations to further unravel the relationship between temperature rise, amorphization and Hugoniot behaviors up to a pressure level of 100 GPa. These investigations underline the power of computational methods to unravel the physics in complex shock experiments.

Bio:
Professor Ghatu Subhash obtained his PhD from University of California San Diego in 1991 and conducted his post-doctoral research at California Institute of Technology during 1992-93. He is currently Newton C Ebaugh Professor in Mechanical and Aerospace Engineering department at University of Florida (UF). His research focusses on dynamic multiaxial behavior of advanced ceramics, metals, composites, gels and biological materials. He has developed novel experimental methods which have been patented and widely used among the high strain rate experimental mechanics community. He has coauthored 205 peer reviewed journal articles (>8600 citations in Google Scholar, h-index=49), 85 conference proceedings, 2-books, and 6 patents. He has poneered the concept of ‘Dynamic Hardness’ which is patented in US and Canada, and widely used by researchers to quickly evaluate the material resistance to dynamic loads. Most recently, he has developed a novel ‘millipede bar’ which has many applications in construction and machine tool industry. Dr. Subhash has graduated 35-PhD students. For his exceptional dedication to graduate education he was awarded 2020-2021 Doctoral Dissertation Advisor/Mentoring Award by the University of Florida. He is a Fellow of three societies: ASME, Society for Experimental Mechanics (SEM), and the American Ceramic Society. He serves as the Co-Editor-in-Chief of Mechanics of Materials journal. Dr. Subhash has received numerous awards from professional societies: SEM Lazan Award (2021) for innovative contributions to experimental mechanics, SEM ‘Frocht Award’ (2018) for outstanding achievements as an educator, ‘Best Paper’ award - ASME Journal of Engineering Materials and Technology, ‘Significant Contribution Award’ from the American Nuclear Society, ‘Technology Innovator Award’ from UF, ASME Student Section Advisor Award, ‘SAE Ralph R. Teetor Educational Award’, and ‘ASEE Outstanding New Mechanics Educator’ award. He is currently on sabbatical at EPFL and enjoying the beautiful Lausanne and Switzerland.
Read more

Title: Why things don’t work — On the foundations of mathematics and methodological barriers in computations and AI

Anders Hansen leads the Applied Functional and Harmonic Analysis group within the Cambridge Centre for Analysis at DAMTP. He is a Reader (Associate Professor) in mathematics at DAMTP, Professor of Mathematics at the University of Oslo, a Royal Society University Research Fellow and also a Fellow of Peterhouse.

His interests include Functional Analysis (applied), Foundations of Computations, Artificial Intelligence, Compressed Sensing, Optimisation, Operator/Spectral Theory, Numerical Analysis, Computational Harmonic Analysis, Mathematical Signal Processing, Sampling Theory, Inverse Problems, Medical Imaging, Geometric Integration, Operator Algebras

Abstract: The alchemists wanted to create gold, Hilbert wanted an algorithm to solve Diophantine equations, researchers want to make deep learning robust in AI, MATLAB wants (but fails) to detect when it provides wrong solutions to linear programs etc. Why does one not succeed in so many of these fundamental cases? The reason is typically methodological barriers. The history of science is full of methodological barriers — reasons for why we never succeed in reaching certain goals. In many cases, this is due to the foundations of mathematics. We will present a new program on methodological barriers and foundations of mathematics, where — in this talk — we will focus on two basic problems: (1) The instability problem in deep learning: Why do researchers fail to produce stable neural networks in basic classification and computer vision problems that can easily be handled by humans — when one can prove that there exist stable and accurate neural networks? Moreover, AI algorithms can typically not detect when they are wrong, which becomes a serious issue when striving to create trustworthy AI. The problem is more general, as for example MATLAB's linprog routine is incapable of certifying correct solutions of basic linear programs. Thus, we’ll answer the following question: (2) Why are algorithms (in AI and computations in general) incapable of determining when they are wrong? 


Read more

"Machine learning in chemistry and beyond" (ChE-650) seminar by Prof. Volker Deringer (University of Oxford)

Volker Deringer studied chemistry at RWTH Aachen University (Germany), where he obtained his diploma (2010) and doctorate (2014) under the guidance of Richard Dronskowski.
In 2015, he moved to the University of Cambridge as a fellow of the Alexander von Humboldt Foundation; in 2017, he was awarded a Leverhulme Early Career Fellowship at the same institution. He joined the Inorganic Chemistry Laboratory of the University of Oxford in September 2019. In addition to his Associate Professorship in the Department, he holds a Tutorial Fellowship at St Anne's College, Oxford.


Read more

Data Management Planning Bootcamp

EPFL Library Research Data Team

Planning your data management is an adventure with no end ! That's why we want to offer you a bootcamp, whatever your experience with data management is.
In this bootcamp, you will be able to :
  • Ask any question about research data management to a team of experts
  • Set up a strategy for data management planning (in the form of a DMP or not)
  • Get feedback from your peers about your challenges
The bootcamp starts at 09:00 with a short introduction and has an open end based on your needs.
The bootcamp is for all levels, so if you are totally to research data management, we encourage you to check the following resources beforehand:

Read more

Title tba

Lucy Colwell, Cambridge University – Google
 


Read more

IC Dean Handover Ceremony

Jim Larus, Rüdiger Urbanke, Jan Hesthaven, Edouard Bugnion, Pierre Dillenbourg, Sabine Süsstrunk, Anne-Marie Kermarrec  

After eight years at the helm, Professor James Larus steps down as Dean of EPFL’s School of Computer and Communication Sciences in September to leave his place to Professor Rüdiger Urbanke, an expert in powerful channel coding methods and who has been with EPFL since 1999.
Find out more: https://news.epfl.ch/news/imagine-living-without-the-internet-search-or-em-2/

Program: 17h30: start of the ceremony, followed by an aperitif. 

Registration is required and entry to the Forum is only permitted upon presentation of the COVID Certificate with QR code. Please bring your identitiy card and a mask, and present yourself at least 30 mins before the start of the event at the entrance.  

Registration: https://go.epfl.ch/dean-handover-ceremony

 


Read more

EPFL Workshop on 'New Horizons in MRI'

Prof. Andrew Webb, Leiden University.  Prof. Klaus Scheffler, Max Planck Insitute, Tübingen. Prof. Nicole Seiberlich, University of Michigan. Prof. Michael Lustig, UC Berkeley. Prof. Benedikt Poser, Maastricht University. Prof. Kawin Setsompop, Stanford University. 

MRI is one of the most powerful and versatile modalities for medical imaging. Far beyond the initial expectations, the modality has kept improving steadily both in terms of performance and scope during the past few decades, and shows no sign of slowing down.

To identify the hottest topics and future trends in MRI research, EPFL is organising a full day of discussion and brainstorming with world-leading experts in the field. The full program is available on https://go.epfl.ch/mri. 

The workshop will be broadcasted live online for free! To receive access to the webinar, please register on the dedicated webpage. Note that due to the current sanitary situation, attendance of the physical event is restricted to invited guests.

 


Read more

Towards essentially decentralized interior point methods for distributed non-convex optimization

Alexander Engelmann

Title:
Towards essentially decentralized interior point methods for distributed non-convex optimization

Speaker:
Alexander Engelmann

Abstract:
Distributed and decentralized optimization methods are key in distributed model predictive control, in distributed sensing, and estimation. Non-linear models, however, lead to problems with non-convex constraints for which established distributed and decentralized algorithms often lack convergence guarantees. Moreover, decentralized algorithms frequently exhibit rather slow linear convergence rates. In this talk we propose an essentially decentralized primal-dual interior point method with local convergence guarantees for non-convex problems at a superlinear rate. We draw upon different examples from power systems and control illustrating its performance. The numerical results indicate that the proposed method is able to outperform ADMM in terms of computation time and it has the potential to overcome difficulties associated with active-set detection in the context of distributed optimization.

Bio:
Alexander Engelmann (GSM'18) received the B.Sc. and M.Sc. degrees in electrical engineering and computer science (with distinction) from the Karlsruhe Institute of Technology, Karlsruhe, Germany, in 2014 and 2016, respectively, where since 2017, he has been working toward the Ph.D. degree with the Optimization and Control group, Institute for Automation and Applied Informatics, where he is focusing on distributed optimization and optimal control for power and multi-energy systems.


Read more

IMX Seminar Series - Operando modeling of realistic functional nanoporous materials

Prof. Veronique van Speybroek, Center for Molecular Modeling, Belgium

Nanoporous materials having pores with dimensions less than 100 nm, are omnipresent in many application fields such as catalysis, separation, energy storage, etc. The ultimate dream would be to design materials to specific needs such as having the desired surface area, nanoconfinement, etc. This is a very ambitious goal both for theoreticians and experimentalists, as one is confronted with an inherent problem of attainable length and time scales. From experimental characterization point of view, one tries to push the limits of spatial and temporal resolution to systematically smaller scales, whereas modeling typically adopts a bottom-up approach, starting from atomistic information and trying to bridge to experimental scales. So far, theoretically attainable length scales within the field of nanostructured materials are limited to a few tens of nanometers and common molecular dynamics (MD) runs extend well into the nanosecond range, depending on the level of theory used to calculate the forces between the atoms.
Additionally, it is important to realize that the functional response of materials is largely affected by the conditions in which they do the work. Therefore, it is essential to account in a modeling approach for so called operando conditions taking into account realistic temperatures, pressures, presence of moisture, etc. Operando modeling can certainly not be achieved with one single technique. Instead a range of models based on molecular dynamics (MD) methods, microkinetic models, and machine learning algorithms are currently explored. Within this talk, I will highlight how advanced molecular dynamics simulations can help in understanding the function of nanoporous materials under operating conditions. I will illustrate various modeling concepts by examples in the field of zeolite catalysis, phase transformations in Metal-organic Frameworks. It will become clear how modeling in close synergy with experiment is quintessential in understanding the function of nanostructured materials. I will end with some perspectives on modeling spatiotemporal behavior in nanoporous materials.


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Marcel Salathé

Prof. Marcel Salathé


The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   

The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/65380598263


Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, September 27th, 2021 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages
Read more

EPFL Connect Design X Startup



The EPFL Startup Launchpad is pleased to invite you to its fourth edition of EPFL Connect on Monday 27 September 2021 from 18:00 to 19:45 - online via Zoom.

Entrepreneurs from EPFL entrepreneurship programmes, alumni from EPFL, UNIL, IMD and ECAL, as well as all innovation enthusiasts are welcome to attend this networking event focusing on the contribution of design for early-stage technology startups.

You will have the opportunity to discover how design has contributed to 2 startups, then you will have the opportunity to benefit from the collective intelligence to gather ideas for your project and to identify opportunities to collaborate with people from the fields of design and innovation.

Agenda
17:45 Technical welcome of the participants
18:00 Welcome words from the organisers
18:10 Thematic networking session
18:30 Panel discussion on the topic "Design X Startup"
19:10 Sharing experiences in small groups
19:45 End of the event

If you want to expand your network and learn from other startups and designers, join us at our next EPFL Connect.

The event is free but registration is required before Wednesday 22 September 2021.


Read more

MechE Colloquium: Coupling rheology and segregation in granular flows

Prof. Nico Gray, Department of Mathematics, University of Manchester

Abstract:
During the last fifteen years there has been a paradigm shift in the continuum modelling of granular materials; most notably with the development of rheological models, such as the μ(I)-rheology (where μ is the friction and I is the inertial number), but also with significant advances in theories for particle segregation. This paper details theoretical and numerical frameworks (based on OpenFOAM®) which unify these currently disconnected endeavours. Coupling the segregation with the flow, and vice versa, is not only vital for a complete theory of granular materials, but is also beneficial for developing numerical methods to handle evolving free surfaces. This general approach is based on the partially regularized incompressible μ(I)-rheology, which is coupled to the gravity-driven segregation theory of Gray & Ancey (J. Fluid Mech., vol. 678, 2011, pp. 353–588).
These advection–diffusion–segregation equations describe the evolving concentrations of the constituents, which then couple back to the variable viscosity in the incompressible Navier–Stokes equations. A novel feature of this approach is that any number of differently sized phases may be included, which may have disparate frictional properties. Further inclusion of an excess air phase, which segregates away from the granular material, then allows the complex evolution of the free surface to be captured simultaneously. Three primary coupling mechanisms are identified: (i) advection of the particle concentrations by the bulk velocity, (ii) feedback of the particle-size and/or frictional properties on the bulk flow field and (iii) influence of the shear rate, pressure, gravity, particle size and particle-size ratio on the locally evolving segregation and diffusion rates. The numerical method is extensively tested in one-way coupled computations, before the fully coupled model is compared with the discrete element method simulations of Tripathi & Khakhar (Phys. Fluids, vol. 23, 2011, 113302) and used to compute the petal-like segregation pattern that spontaneously develops in a square rotating drum.

Link to the paper: https://doi.org/10.1017/jfm.2020.973
And movie: https://static.cambridge.org/content/id/urn:cambridge.org:id:article:S0022112020009738/resource/name/S0022112020009738sup006.mp4

Bio:
Nico Gray is a professor of Applied Mathematics in the Department of Mathematics and the Manchester Centre for Nonlinear Dynamics at The University of Manchester. He is an expert on granular flows and the particle segregation that takes place within them. This has applications to a wide range of common industrial processes, as well as to geophysical flows such as avalanches and debris flows. Nico holds a BSc in Mathematics from the University of  Manchester, a PhD from the University of Cambridge and a Habilitation in Continuum Mechanics and Geophysical Mechanics from the Technical University of Darmstadt in Germany.
Read more

AMLD 2021 Workshop – Federated Learning: collaborative machine learning on sensitive decentralized data



⚠️ A valid COVID certificate must be presented on site to enter the event. ⚠️

Datasets of interest in many application domains (e.g. healthcare, finance data, manufacturing) contain sensitive or private information and cannot easily be shared. Additionally, such data frequently belongs to multiple distinct parties and combining it in one location would expose a lucrative target to hackers. Therefore, it is desirable to make use of such data without a need to disclose it or store it in a central location. 

Unfortunately, traditional methods to train predictive models expect data to be fully accessible and centralized on a single server. Research work therefore has to rely on small or artificial datasets that can safely be centralized. As a result, findings frequently do not generalize well to real-world datapoints and progress is hampered. 

Federated Learning (FL) is a recently introduced paradigm that addresses this limitation by training models on decentralized datasets without requiring centralized data access. This approach allows multiple distinct parties to collaboratively train predictive models without a need to directly share sensitive data. Instead of combining datasets, FL trains a model in multiple iterations on data subsets stored in different locations. In every iteration, every party owning a data subset downloads a copy of the current model weights. An updated model is computed for each data subset in a local training step. Per-party model updates are then aggregated (a step that can be centralized, as it does not require data access) resulting in a single overarching FL update step. 

As an introduction to the workshop, we will introduce the basic concepts underlying FL and discuss a few of the key related topics (e.g. Differencial Privacy, 
Model Encryption). Our focus however, will be on gaining hands-on experience. We will implement a simple Federated Learning system using tensorflow (tensorflow/federated) and pytorch (PySyft). We will give a quick introduction to all needed libraries and tools at the start.

 
Read more

AMLD 2021 Workshop – Fraud detection with unsupervised ML



⚠️ A valid COVID certificate must be presented on site to enter the event. ⚠️

In many fraud- (or general outlier-) detection situations, labelled data is not available. We therefore need to resort to unsupervised methods to identify points that are somehow untypical. In this workshop, a short introduction will be given that discusses the main outlier detection methods (from the classic LOF to modern algorithms such as Isolation Forest, Autoencoders and Adversarial networks) and appropriate metrics for highly imbalanced datasets.
Then, participants will be given unlabelled datasets to make predictions on. Scores will be compared on a leader board, with the emphasis on comparing techniques.
Read more

AMLD 2021 Workshop – Flatland: Multi-Agent Reinforcement Learning for Trains



⚠️ A valid COVID certificate must be presented on site to enter the event. ⚠️

This workshop is a great introduction to the Enabling cooperation between multiple agents: information sharing in Multi-Agent Reinforcement Learning workshop.

Scheduling trains is hard: railway networks are growing fast, and the decision-making methods commonly used don't scale well. How can we solve this problem? With machine learning, of course! In this workshop, we will use reinforcement learning to tackle this real-world challenge.
In the morning, we will introduce the main reinforcement learning methods. Participants will get familiar with them by solving toy problems. In the afternoon, participants will design their own agents, which will then compete with other people’s agents in a (friendly) competitive setting.

We will use the Flatland railway simulator, developed in collaboration with SBB and Deutsche Bahn. We plan to invite SBB researchers to give insights on this problem, as well as competitive participants from previous Flatland challenges. Following this workshop, participants can take part in the other full-day Flatland workshop organized by Deutsche Bahn and InstaDeep, which will introduce the bleeding-edge innovations they have been working on to tackle this problem.
Read more

AMLD 2021 Workshop – Graph Neural Networks for structured data



⚠️ A valid COVID certificate must be presented on site to enter the event. ⚠️

A quick introduction into using Graph Neural Networks and their application to structured data.

Participants will learn basics of GNNs, how to prepare training data (from a set of SQL tables) and train GNNs with it.
Read more

lunch&LEARN: Developing expertise - a practical approach to teaching in hands-on settings

Siara Isaac, Roland Tormey

Labs, studios, fieldwork, and projects are key opportunities for the deliberate practice engineering students need to develop their disciplinary skills. Drawing on research on the nature and development of 'expertise', we provide evidence-informed and practical approaches to teaching in hands-on settings from our newly published book Facilitating Experiential Learning in Higher Education. While the book also addresses providing feedback, structuring explanations, and managing relationships with a class, this session will include activities on how to formulate and employ questions to maximise the rich learning potential of hands-on environments.
 

Seems interesting? Join us by registering here.
After registration you will receive a link to the Zoom room.

--------------------------
The lunch&LEARN series was created by the Center LEARN to stimulate the exchange between learning science researchers and everyone at EPFL interested in teaching. Our sessions seek to either translate learning research into teaching practice or provide evidence and insights from teaching practice. Video recordings and slides from previous sessions can be found on the lunch&LEARN webpage. During this COVID-19 impacted period, we turned it into a remote coffee&LEARN.

Read more

AMLD 2021 Workshop – Shedding Light on obscure Graph Deep Learning



⚠️ A valid COVID certificate must be presented on site to enter the event. ⚠️

Ever wondered why that molecule is hydrophobic? Or why a region is constantly jammed with traffic? Or why certain people in a social network might know each other?

All these problems can be modelled by using powerful data structures: graphs, made of entities (nodes, such as the atoms of a molecule) and relationships (edges between the nodes, such as the chemical bonds). These can be fed into machine learning models which leverage relationship information for predictions: for example, a model can be trained to classify whether a molecule will be hydrophobic or not. In particular, deep learning (DL) has recently been extended to work on graphs, with the advent of graph neural networks (GNNs). 

Up until now and like in many other domains, deep learning on graphs, albeit powerful, was completely obscure. In fact, DL models all lack inherent interpretability.
With the recent introduction of post-hoc interpretability techniques, light was shed on several DL models. Last year, this was made possible on graphs too, thanks to the advent of several new interpretability techniques.
This opens up a world of possibilities to better understand how these models leverage complex relationships between entities during their predictions.

During this workshop, the participants will learn how to model a variety of problems using graphs, train GNNs on them and apply state-of-the-art techniques to interpret the underlying motivations that led to their predictions.
Read more

AMLD 2021 Workshop – No mercy for manual entry



⚠️ A valid COVID certificate must be presented on site to enter the event. ⚠️

Machine Learning (ML) is having a huge impact in the automation of tedious and repetitive tasks in several industries. In this workshop, we take the example of the digitalization of paper documents to show how standard ML techniques can have a big impact in this context.

Many institutions deal every day with a large number of paper documents (invoices, vouchers, …). These documents are often treated by employees with a high business knowledge and entered manually in a database or in another type of data storage. This is clearly an inefficient way to use resources. Therefore, the automation of this task is a priority to many institutions.

The goal of this workshop is to show you how ML can be used in the automation of such a process. You will see how to implement algorithms to:
• Classify scanned documents (using a CNN model implemented with fastai)
• Detect the position of a few fields within the document (using Detectron2) 
• Extract the information from these fields (using Tesseract)
• Use the human feedback to improve the system performance (human-in-the-loop  or HITL).
Read more

AMLD 2021 Workshop – From Sketch(y) to Picture(sque) with Deep Learning



⚠️ A valid COVID certificate must be presented on site to enter the event. ⚠️
  • Item retrieval systems are well implemented in our daily lives, but few are aware of how they are powered.
  • Speaker Identification, Face recognition, Targeted advertisement are all examples of Item retrieval systems.
  • During this workshop we will present what are the mechanisms behind those systems and see how we can implement one of them.
  • We will setup a complete sketch-based image retrieval pipeline, from the processing of the dataset to the deployment of a small web app, including the engineering of the Deep learning model powering it.

Read more

NeuroTech Talk series - Non-Invasive Brain Interfaces

Daniel Månsson, CEO of Flow NeuroscienceOlivier Oullier, cofounder of Inclusive Brains, Quentin Soulet de Brugière, CEO and co-founder of Dreem

In collaboration with the Center for Neuroprosthetics (CNP)  at EPFL, Innovation Forum Lausanne is organizing the NeuroTech Talk series. This conference series revolves around industrial applications in the fields of neuroscience and neuroprosthetics. The goal of this project is to broaden the view of researchers on what's outside academia. Beyond the science behind these applications, the seminars will focus on the personal, entrepreneurial challenges coming with the clinical translation of advances in neurotechnology. Speakers will share their career paths, the choices that brought them where they are today and their advices for PhD students and researchers seeking a future in the medical device industry.

This session taking place on 29th Sept. 2021 at 18:00 CET will focus on Non-invasive brain interfaces. Professor Silvestro Micera, head of the Translational Neural Engineering Lab at EPFL, will be leading the seminar and introducing the speakers:

Registration for the conference is mandatory and can be carried out for free here. The link to access the online conference will be communicated after registration. Be sure to stay tuned for future events in this talk series.
Read more

Keep students motivated in your online or on campus course

Isabelle Sarrade

At the end of this workshop you should be able to:
-Choose an appropriate strategy to maintain student motivation to attend and participate in your class.
-Explain and identify what gets students motivated during on campus or online classes.
Drawing on motivation theories and recent research on online learning during the COVID confinement, we shall discuss what elements of flexible teaching can motivate or demotivate attendance and participation in class.


Read more

Beyond structure and composition: Multidimensional TEM as a key for imaging electric fields, 3D shape and soft matter

Prof. Knut Müller Caspary - LMU Munich

In recent years, the dimensionality in transmission electron microscopy (TEM) has increased rapidly by the advent of ultrafast cameras that record at frame rates of many kHz. This development has especially paved the way for a revolution as to the versatility of scanning TEM (STEM). In particular, momentum-resolved STEM enhanced traditional Z- and phase-contrast techniques such that any conventional imaging mode is present simultaneously in a 4D data set. Most importantly, the combination of real- and reciprocal space information nowadays allows to quantify electric fields, charge densities and potentials with subatomic resolution, to measure polarisation-induced electric fields, and to solve the phase problem by ptychographic techniques.
In this presentation, a brief review of quantitative STEM is given, followed by selected works on ultrafast detectors. We demonstrate the capability of 4D-STEM using several examples such as the mapping of atomic electric fields in 2D materials and ptychographic reconstructions using different algorithms. Moreover, we report the recent development of focal series 4D STEM yielding insights into the scattering dynamics and 3D shape of specimen. The talk closes with prospects on ultrahigh time resolution for imaging (magnetic) dynamics at GHz frequencies, and opportunities for high-contrast imaging of soft matter at low doses, building a bridge between materials science methodology and life science challenges.


Biosketch
Knut Müller-Caspary received his Ph.D from Bremen University (Germany) in 2011. Between 2011 and 2016 he worked as a postdoctoral research fellow in Bremen focussing on strain, composition and electric field mapping by momentum-resolved STEM. He established cooperations with several companies to explore new detectors as to speed, dynamic range, efficiency and in-situ capability. In particular, he contributed key developments to the mapping of atomic electric fields and charge densities at subatomic scale by exploiting the full complexity of STEM diffraction patterns. In 2016 Müller-Caspary moved to the EMAT institute at the University of Antwerp (Belgium) where he applied STEM to the electrical characterisation of 2D materials. In 2018 he established a Helmholtz Young Investigator Group for momentum-resolved STEM at Forschungszentrum Jülich (Germany) and became junior professor at RWTH Aachen University in 2019. In 2021, Knut Müller-Caspary moved to the faculty of chemistry and pharmacy at Ludwig-Maximilians-University Munich as university professor for TEM.


Read more

IMX Seminar Series - PIC hydrogels as versatile synthetic and highly biomimetic matrix materials

Prof. Paul Kouwer, Radbud University, The Netherlands

Radboud University, Institute for Molecules and Materials, Heyendaalseweg 135, 6525 AJ Nijmegen, the Netherlands, p.kouwer@science.ru.nl
Fibrous hydrogels are omnipresent in the human body. At very low protein concentrations, they form stable, porous networks that are the basis for mechanical characteristics of cytoskeleton and of the extracellular matrix. The biogels in our bodies are not static; they respond to physical, chemical and cellular cues that adapt their properties.
Such architecture and behavior are not readily realized in synthetic materials. Recently, however, we developed a hydrogel that closely mimics the fibrous architecture as well as the linear and nonlinear mechanical properties of cytoskeletal and extracellular matrix materials. The synthetic nature of the material allows us to vary endlessly in molecular structure and derivatization with functional (bio)molecules.
In addition, our lab studies various applications of the biomimetic PIC gel, ranging from immunotherapy to wound care and dental therapies to 3D cell cultures. In any application, the PIC gel is precisely tailored in mechanical properties and biofunctionalization to drive the desired cell response. Mixed expertise in the research group ensures that innovations in hydrogel engineering, for instance features for in situ and reversible stiffness changes, can be directly applied in a biological context.
In this talk, I will introduce PIC gels, their structure and approaches how to controllably change the physical and biological properties. In addition, I will give various examples on how PIC properties may be used to affect cellular responses.
 
Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Pavan Ramdya

Prof. Pavan Ramdya

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   
 
The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/83759099644

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, October 4th, 2021 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

Eliminate implicit bias in your teaching

Iris Capdevila and Isabelle Sarrade

This interactive online workshop explains the underlying mechanics of implicit bias and of stereotypes and it gives examples drawn from current research in STEM education. The workshop also presents instructional resources that support diversity, inclusion and equity (DIE) in the classroom.
At the end of the workshop participants will be able to:

  • Define implicit biases and provide examples linked to gender, abilities and ethnicity.
  • Explain how implicit bias awareness helps to improve teaching.
  • Plan teaching sessions and activities that support learning and eliminate implicit biases.

Read more

MechE Colloquium: The hydrodynamics of propulsion in rowing

Prof. Jerry Westerweel, Mechanical, Maritime and Materials Engineering, Process and Energy, Fluid Mechanics, TU Delft

Abstract:
In order to improve the performance in rowing contests, we built a Ro(w)bot in which we can perform detailed measurements around a 1:2 scale model of an actual rowing blade that moves along a realistic path through water. The set-up allows us to measure both the forces and the impulsive flow by means of time-resolved PIV. We first investigated a more academic case of an accelerating rectangular plate along a straight path, which matches the first stroke at the start of a race. This showed that the forces during the acceleration phase are considerably higher than for steady motion. Also, it demonstrated that there is an optimal depth below the water surface that maximises the drag force. In the second phase of this study we considered the complete motion of an actual rowing blade. This revealed that the generated impulse is not aligned with the propulsive direction, indicating that the propulsion is suboptimal. A simple adjustment is proposed to optimise the alignment of the leading and trailing edge vortices that achieves an improved alignment of the generated impulse with respect to the motion of the boat.

Bio:
J. Westerweel obtained is M.Sc. degree in applied physics in 1988 at the Delft University of Technology, where he also obtained in Ph.D. degree in 1993. He then became a Research Fellow at the Royal Netherlands Academy of Arts and Sciences, and worked as a visiting scholar at Stanford University, the California Institute of Technology, and the University of Illinois at Urbana-Champaign. In 2001 he was appointed as a Anthoni van Leeuwenhoek professor at the Delft University of Technology, and since 2005 he holds the fluid mechanics chair at the Faculty of Mechanical, Maritime and Materials Engineering.
His research interests are turbulence, dispersed multiphase flows, microfluidics, biological fluid dynamics, impulsive flows, and the fluid dynamics of sports. He is the (co-) author of a text book on particle image velocimetry and one on turbulence. He has been an Editor-in-Chief for ‘Experiments in Fluids’ since 2012.
Read more

"Machine learning in chemistry and beyond" (ChE-650) seminar by Prof. Andrew White (University of Rochester): Making cool stuff with deep learning

Andrew White graduated from Rose-Hulman Institute of Technology in 2008 with a BS in chemical engineering. While at Rose, he spent a year studying at the Otto-von Guericke Universität and the Max Planck Institute for Dynamics of Complex Technical Systems in Magdeburg, Germany. Dr. White completed a PhD in chemical engineering at the University of Washington in 2013. The thesis topic was the creation of non-fouling biomimetic surfaces with computational modeling. Next, Dr. White worked with Professor Greg Voth at University of Chicago as a Post-doctoral fellow in the Institute for Biophysical Dynamics from 2013-2014. In Chicago, he developed new methods for combining simulations and experiments. Dr. White joined the University of Rochester in Chemical Engineering in 2015 and is currently an associate professor. He has joint appointments in the Chemistry Department, Biophysics, Materials Science, and Data Science programs. Dr. White received a National Science Foundation CAREER award in 2018 and an Outstanding Young Investigator Award from the National Institutes of Health in 2020. Dr. White has authored a textbook on deep learning for molecules and materials, which is freely available at https://whitead.github.io/dmol-book.

Deep learning has begun a renaissance in chemistry and materials. We can devise and fit models to predict molecular properties in a few hours and deploy them in a web browser. We can create novel generative models that were previously PhD theses in an afternoon. In my group, we’re exploring deep learning in soft materials and molecules. We are focused on two major problems: interpretability and data scarcity. Now that we can make deep learning models to predict any molecular property ad naseum, what can we learn? I will discuss our recent efforts on interpreting deep learning models through symbolic regression and counterfactuals. Data scarcity is a common problem in chemistry: how can we learn new properties without significant expense of experiments? One method is in judicious choose of experiments, which can be done with active learning. Another approach is pre-training or meta-leraning, which tries to exploit related data. I will cover recent progress in these areas. Finally, one consequence of the state of deep learning is that you can just make cool things in chemistry with minimal effort. I’ll review a few fun projects, including making molecules by banging on the keyboard, doing math with emojis, finding chemical entities in HTML, and doing molecular dynamics with ImageNet derived potentials.

 


Read more

Améliorer l'expressivité et sa voix pour ses cours

Rita Gay

Comment penser son contenu pou pouvoir bien le dire? En quoi la voix est une résultante du corps en action? Quelles technique vocales mettre en œuvre et exercer?


Read more

IMX Seminar Series - TBD

Prof. Christos Panagopoulos, Nanyang Technological University, Singapore


Read more

MechE Colloquium: Stability and body mechanics during swimming in fish

Prof. Eric Tytell, Department of Biology, Tufts University

Abstract:
Most fishes are statically unstable. Without active movements of their bodies and fins, they cannot maintain a normal upright posture. The swimming movement itself is also unstable, since the thrust force from the tail is located behind the center of mass. Despite these intrinsic instabilities, most fish are dynamically stable to a wide range of perturbations. How do they maintain stability? My lab has been investigating this question both experimentally and computationally. We are quantifying static stability by measuring the location of the center of mass and center of buoyancy in fishes. Even in a computational model with constant density, different body shapes and stiffnesses have different stability. We are also considering dynamic stability by perturbing fish with a water jet and describing the fin movements they use to compensate. These fin movements appear to be driven by the central nervous system, but are strongly dependent on sensory inputs from mechanosensors in the fin. By controlling the fins, fish can regulate whole-body posture, but also the twisting movements of different parts of the body. These twisting movements, in turn, may generate upward forces to maintain or change position vertically. With these studies, we are starting to identify some of the key ways in which fish maintain stability in three dimensions.

Bio:
Eric D. Tytell received the B.A. degree from the University of North Carolina at Chapel Hill in Biology and Physics in 1998, then the M.Phil. from the University of Cambridge in Zoology in 1999, and the Ph.D. degree in Biology from Harvard University in 2005.

He is an Associate Professor in the biology department at Tufts University, where his laboratory works on the biomechanics, muscle physiology, and neural control of swimming in a wide range of fish species, including experimental and computational work on individual fish and on schools of interacting fish. He enjoys hiking with his wife and two children, running, skiing, and playing board games. For more information, see the lab website here: https://sites.tufts.edu/tytelllab/.
Read more

"Machine learning in chemistry and beyond" (ChE-650) seminar by Miguel Caro (Aalto University)

Miguel Caro is originally from a small town (Cartaya) in southwestern Spain. He graduated with a Physics degree from University of La Laguna, Tenerife, Spain. He then moved to Cork, Ireland, where he pursued a PhD in computational condensed-matter physics under Prof. Eoin O’Reilly at the Tyndall National Institute. His thesis work, for which he was awarded his PhD in 2013, focused on theory of III-N alloys, a material system widely used for optoelectronic applications. After the PhD, he moved to Aalto University, Finland as a postdoc in 2013. In 2017 he obtained the Academy of Finland Postdoctoral Researcher grant and since 2020 he is Academy of Finland Research Fellow. Dr. Caro’s current research interests concern the atomistic simulation of real materials, especially carbon-based materials, using a battery of simulation tools and methodologies, from density functional theory to machine learning.


Read more

IMX Seminar Series - TBD

Prof. Jason Burdick, University of Pennsylvania, USA


Read more

"Machine learning in chemistry and beyond" (ChE-650) seminar by Marwin Segler (Microsoft Research)

Dr. Marwin Segler is Senior Researcher at Microsoft Research. Before that, he was researcher at BenevolentAI and PhD student at WWU Muenster, where he worked on planning chemical synthesis with deep neural networks and symbolic AI.


Read more

DARPA Assessing Immune Memory (AIM) call for proposals



Amount:
The proposed costs must be realistic for the technical and management approach and accurately reflect the technical goals and objectives of the solicitation.  These costs are consistent with the proposer's Statement of Work and reflect a sufficient understanding of the costs and level of effort needed to successfully accomplish the proposed technical approach.

Duration:
48 months

Aim:
Military service members rely on effective vaccination for the prevention of communicable disease as well as to guard against biothreat exposure. Many current vaccines lack durability (i.e., do not provide effective protection over long periods of time), and there are multiple pathogens and threats that lack prophylactic options altogether. It is currently impossible to predict vaccine durability from early response profiles, largely owing to ignorance of mechanisms underlying immune memory as well as an inability to measure the cellular contributors that invoke long-lasting immune protection. Formation of immune memory is a complex physiological process characterized by a diverse array of cellular interactions and signaling processes. AIM seeks to develop a platform capability to predict immune memory informed by a systems-level view of the host response to vaccination and its mechanisms.

Eligibility:
  • All responsible sources capable of satisfying the Government’s needs may submit a proposal that shall be considered by DARPA.
  • Non-U.S. organizations and/or individuals may participate to the extent that such participants
    comply with any necessary nondisclosure agreements, security regulations, export control laws,
    and other governing statutes applicable under the circumstances.
How to apply:

Agency Contact:
The BAA Coordinator for this effort may be reached at:
AIM@darpa.mil
DARPA/BTO
ATTN: HR001121S0037
675 North Randolph Street
Arlington, VA 22203-2114
The Research Office strongly encourages interested investigators to contact the BAA Coordinator PRIOR to working on the proposal.  The Coordinator is available to discuss project ideas, budget, etc.

EPFL Contact:

 
Read more

IMX Seminar Series - TBD

Prof. Shimpei Ono, Central Research Institute of Electric Power Industry, Japan


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Semyon Malamud

Prof. Semyon Malamud

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   
 
The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/83759099644

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, November 1st, 2021 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

"Machine learning in chemistry and beyond" (ChE-650) seminar by Alexei Lapkin (University of Cambridge)

  Alexei Lapkin studied chemistry at Novosibirsk State University (Russia) and obtained a PhD degree at the University of Bath for his work on multifunctional catalytic reactors (under supervision of late Professor W.J. Thomas). He joined Cambridge in 2013 as a Professor of Sustainable Reaction Engineering. Alexei is involved in the advisory boards of Reaction Chemistry and Engineering (RSC) and Sustainable Chemistry and Pharmacy (Elsevier) journals. He is an associate editor for Chemical Engineering section of Frontiers of Chemistry journal. He is a member of Scientific Advisory Board of the International Sustainable Chemistry Collaborative Centre (ISC3).


Read more

CIS - Digital Twin Days



Monday November 15 and Tuesday November 16, 2021 at SwissTech Convention Center (STCC EPFL)

Digital Twin technologies are gaining momentum in research and applications in health and industry on an international scale. EPFL and its partners are active in the development of related core technologies and their integrations, for instance via the CIS Research Pillars and DIGIPREDICT.
With the EPFL CIS Digital Twin Days 2021, the EPFL Center for Intelligent Systems and its partners want to further increase the awareness for Digital Twin technologies, to showcase their applications for society and industry and to foster the dialogue between researchers, industry representatives and stakeholders from politics and the general public.
Participants 
International renowned researchers, industry representatives and stakeholders from politics 
  • 15 November: scientific conference, thematic event e.g., medical applications, digital twin of physical systems, AI for smart wearables. Presentations by renowned researchers from Academia.
  • 16 November: Digital twin for industry, start-ups and stakeholders from politics: industry and start-up presentations.


Covid Safe
This is a Covid-free event. A valid Covid pass must be presented at the door. 
COVID CERTIFICATE IS ISSUED: to fully vaccinated persons, to persons cured of COVID less than 6 months ago, to persons with a negative PCR test (max 72h) / or antigenic test (max 48h), all persons must present the official QR code and their ID. 
 
Read more

IMX Seminar Series - TBD

Prof. Tony Rollett, Carnegie Mellon University, USA


Read more

"Machine learning in chemistry and beyond" (ChE-650) seminar by Alexandre Tkatchenko (University of Cambridge): On Electrons and Machine Learning Force Fields

Alexandre Tkatchenko is a professor at the Department of Physics and Materials Science (and head of this department since January 2020) at the University of Luxembourg, where he holds a chair in Theoretical Chemical Physics. Tkatchenko also holds a distinguished visiting professor position at Technical University of Berlin. His group develops accurate and efficient first-principles computational models to study a wide range of complex materials, aiming at qualitative understanding and quantitative prediction of their structural, cohesive, electronic, and optical properties at the atomic scale and beyond. He has delivered more than 250 invited talks, seminars and colloquia worldwide, published 180 articles in prestigious journals (h-index of 69 with more than 24,000 citations; Top 1% ISI highly cited researcher in 2018-2020), and serves on the editorial boards of Science Advances and Physical Review Letters. Tkatchenko has received a number of awards, including APS Fellow from the American Physical Society, Gerhard Ertl Young Investigator Award of the German Physical Society, Dirac Medal from the World Association of Theoretical and Computational Chemists (WATOC), van der Waals prize of ICNI-2021, and three flagship grants from the European Research Council: a Starting Grant in 2011, a Consolidator Grant in 2017, and Proof-of-Concept Grant in 2020.

On Electrons and Machine Learning Force Fields

Machine Learning Force Fields (MLFF) should be accurate, efficient, and applicable to molecules, materials, and interfaces thereof. The first step toward ensuring broad applicability and reliability of MLFFs requires a robust conceptual understanding of how to map interacting electrons to interacting "atoms". Here I discuss two aspects: (1) how electronic interactions are mapped to atoms with a critique of the "electronic nearsightedness" principle, and (2) our developments of symmetry-adapted gradient-domain machine learning (sGDML) framework for MLFFs generally applicable for modeling of molecules, materials, and their interfaces. I highlight the key importance of bridging fundamental physical priors and conservation laws with the flexibility of non-linear ML regressors to achieve the challenging goal of constructing chemically-accurate force fields for a broad set of systems. Applications of sGDML will be presented for small and large (bio/DNA) molecules, pristine and realistic solids, and interfaces between molecules and 2D materials. 

[Refs] Sci. Adv. 3, e1603015 (2017); Nat. Commun. 9, 3887 (2018); Comp. Phys. Comm. 240, 38 (2019); J. Chem. Phys. 150, 114102 (2019); Sci. Adv. 5, eaax0024 (2019).
Read more

IMX Seminar Series - TBD

Prof. Jörg Neugebauer, Max-Planck-Institut, Germany


Read more

"Machine learning in chemistry and beyond" (ChE-650) seminar by Sereina Riniker (ETH Zurich)

Sereina Riniker is currently Associate Professor of Computational Chemistry at the Department of Chemistry and Applied Biosciences of ETH Zurich. 


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Michael Herzog

Prof. Michael Herzog

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   
 
The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/68210109723

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, November 29th, 2021 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

IMX Seminar Series - Atom-scale quantum choreography to the beat of light

Prof. Rupert Huber, Regensburg University, German

Understanding the function of novel quantum materials calls for means to directly watch their elementary building blocks in motion, on their intrinsic length and time scales. Recently, lightwave electronics has made this long-standing dream come true. The idea is to exploit the carrier wave of light as an ultrafast bias to interrogate and control the nanocosm. I will first review how lightwaves can drive electrons in solids, such as 2D materials and topological insulators, into surprising sub-cycle quantum motion. By combining this idea with the spatial resolution of scanning tunneling microscopy we record the first atom-scale slow-motion movies of individual vibrating molecules. Lightwaves inside the tunnelling junction can even serve as femtosecond atomic forces to choreo­graph a coherent structural motion of a single-molecule switch. This concept offers a radically new way of directly watching and controlling key elementary dynamics in nature and steer (bio)chemical reactions or ultrafast phase transitions, on their intrinsic spatio-temporal scales.
 

Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Mark Pauly

Prof. Mark Pauly

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   
 
The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/65551226823

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, December 6th, 2021 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

IMX Seminar Series - TBD

Prof. Feliciano Giustino, University of Texas, USA


Read more

CIS - Colloquium - by Prof. Susan Murphy

  Prof Susan Murphy



The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems. In June 2020, CIS has launched its CIS Colloquia featuring invited notable speakers.
More info
 
Read more

"Machine learning in chemistry and beyond" (ChE-650) seminar by Xiaowei Jia (University of Pittsburgh)

Xiaowei Jia is an Assistant Professor in the Department of Computer Science at the University of Pittsburgh. He obtained my Ph.D. degree at the University of Minnesota, under the supervision of Prof. Vipin Kumar. Prior to that, he got his B.S. and M.S. from the University of Science and Technology of China (USTC) and State University of New York at Buffalo.


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Matteo Dal Peraro

Prof. Matteo Dal Peraro

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   
 
The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/66077101128

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, December 20th, 2021 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Pascal Fua

Prof. Pascal Fua

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   

The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/61326856335

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, January 17th, 2022 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Alexander Mathis

Prof. Alexander Mathis

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   

The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/61911665778

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, January 31st, 2022 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Touradj Ebrahimi

Prof. Touradj Ebrahimi

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   

The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/63510408613

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, February 7th, 2022 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Kathryn Hess Bellwald

Prof. Kathryn Hess Bellwald

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   

The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/67194026582

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, February 7th, 2022 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Jean-Philippe Thiran

Prof. Jean-Philippe Thiran

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   

The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/61304475638

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, March 7th, 2022 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more

CIS - "Get to know your neighbors" Seminar series - Prof. Josie Hughes

Prof. Josie Hughes

The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   

The CIS seminar will take place live on Zoom: https://epfl.zoom.us/j/61206635440 

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, May 2nd, 2022 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages


Read more