February 2022 - Machine-learning-nederland

Reminder: BeNeRL registration, Friday June 3 @ Leiden University
by Moerland, T.M. (Thomas) 28 Feb '22

28 Feb '22

Dear reinforcement learning researcher, A quick reminder to register for the Belgium-Netherlands workshop on Reinforcement Learning (or, if you have already registered, forward this email to an interested colleague). We initially aimed for 75 spots, but RL interest in the region has clearly grown, corona regulations have been lifted, and we managed to book a bigger room, so you can still register through: https://rlg.liacs.nl/benerl-2022<https://rlg.liacs.nl/benerl-2022> (currently at 100 registrations). Hope to see you in June. Kind regards, Thomas Moerland & Aske Plaat

1 0

Thematic seminar: Tomer Koren, Fri March 11, 16h00
by Tim van Erven 25 Feb '22

25 Feb '22

Dear all, We will continue the thematic seminar with a series of online talks. Our next speaker is Tomer Koren from Tel Aviv University. *Tomer Koren *(Tel Aviv University, https://tomerkoren.github.io/) *Friday March 11*, 16h00-17h00 Online on Zoom: https://uva-live.zoom.us/j/85690850169 Meeting ID: 856 9085 0169 Please also join for online drinks after the talk. ** * Benign Underfitting of Stochastic Gradient Descent* We study to what extent may stochastic gradient descent (SGD) be understood as a ``conventional'' learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex optimization framework, where SGD is classically known to minimize the population risk at an optimal rate, and prove that, surprisingly, there exist problem instances where the SGD solution exhibits both empirical risk and generalization gap lower bounded by a universal constant. Consequently, it turns out that SGD is not algorithmically stable in any sense, and its generalization ability cannot be explained by uniform convergence or any other currently known generalization bound technique for that matter (other than that of its classical analysis). Time permitting, we will discuss related results for with-replacement SGD, multi-epoch SGD, and full-batch gradient descent. Based on joint works with Idan Amir, Roi Livni, Yishay Mansour and Uri Sherman. Seminar organizers: Tim van Erven Botond Szabo https://mschauer.github.io/StructuresSeminar/ *Upcoming talks: *Mar. 25, *Nicolò Cesa-Bianchi <https://mschauer.github.io/StructuresSeminar/#CesaBianchi>**, *Università degli Studi di Milano Apr. 22, *Tor Lattimore <https://mschauer.github.io/StructuresSeminar/#Lattimore>*, DeepMind Jun. 10,***Julia Olkhovskaya <https://sites.google.com/view/julia-olkhovskaya/home>*, Vrije Universiteit ** -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

[Jobs] postdoctoral researcher on brain-inspired machine learning
by Lanillos Pradas, P.L. (Pablo) 24 Feb '22

24 Feb '22

The Donders Institute is looking for a postdoctoral researcher on brain-inspired machine learning for DEEPSELF, a joint project between the Donders Institute (Netherlands, supervision: Pablo Lanillos) and Tübingen University (Germany, supervision: Martin Butz), funded by the German Research Foundation (DFG). DEEPSELF is an interdisciplinary project that aims to study the emergence of the agency metacognition ability by learning hierarchical predictive encodings of events. ··············································· Detailed information, candidate profile and application here: https://www.ru.nl/english/working-at/vacature/details-vacature/?recid=11839… Deadline: 6 March 2022 ··············································· If you have any doubt about this great opportunity please do not hesitate to contact me. You will work in an international project team in close collaboration with two PhD candidates and the principal investigators. You will join an exciting and vibrant young team of experts in machine learning, artificial intelligence and robotics, and become part of a big community of ~20 interdisciplinary research projects under the Active Self DFG priority programme umbrella. Thus, you will have the opportunity to take leadership responsibilities and considerably increase the research network. Furthermore, you will participate in summer schools and events organised within the framework of the priority programme. After completion of the project, you will have opportunities to continue in academia and industry. We strongly encourage submissions from different representative minorities. --------------- Dr. Pablo Lanillos (Twitter @PLanillos) Tenured Assistant Professor in Cognitive Artificial Intelligence ELLIS Nijmegen Unit | AI Robotics Lab Donders Institute for Brain, Cognition and Behaviour | Radboud University Nijmegen Prof. Dr. Martin V. Butz Computer Science, Cognitive Modeling Eberhard Karls Universität Tübingen | Germany

1 0

MMLL webinar series
by Joris Mooij 23 Feb '22

23 Feb '22

The Mercury Machine Learning Lab (MMLL) would like to invite you to the MMLL online seminar series. Register now for the kickoff webinar! Date: March 10 Time: 15:00-16:30 Speaker: prof. Juan D. Correa (Universidad Autónoma de Manizales) Title: Generalization of Causal and Statistical Quantities under Transportability and Selection Bias The event will last 1.5 hours in total. It will start with a 20-minute intro about the lab and its objectives, followed by a 40-minute talk by the keynote speaker and a 15-minute Q&A session. The Mercury Machine Learning Lab is a collaboration between University of Amsterdam, Delft University of Technology and Booking.com. The lab focuses on the development and applications of artificial intelligence to the specific domain of online travel booking and recommendation service systems. The MMLL online webinar series will consist of four webinars, focussing on causality, information retrieval, natural language processing, and reinforcement learning. For more details and registration, see https://www.meetup.com/Innovation-Center-for-Artificial-Intelligence/events…

1 0

General Mathematics Colloquium (KdVI) - Max Welling - March 4
by Eni Musta 22 Feb '22

22 Feb '22

Dear colleagues, Our next meeting in the General Mathematics Colloquium series at the Korteweg-de Vries Institute for Mathematics (UvA) is on Friday, March 4 at 16.00. Max Welling (UvA) will speak about "Symmetries in Deep Learning with applications to Molecular Science". The colloquium will be in Science Park 904 room C0.110 and can also be joined via Zoom https://uva-live.zoom.us/j/84560653677<https://eur04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fuva-live.…> If you are interested in attending the talk, the abstract will be announced soon on the colloquium webpage https://staff.fnwi.uva.nl/j.zuiddam/gen-math-colloq/ We are looking forward to seeing you then! Best wishes, Krystal, Eni and Jeroen (Organizers of the General Mathematics Colloquium KdVI)

1 0

CWI seminar Laura Scarabosio
by Wouter Edeling 17 Feb '22

17 Feb '22

Dear all, We are starting again with our CWI seminar for Machine Learning and Uncertainty Quantification for Scientific Computing. The first speaker will be Laura Scarabosio from Radboud University, on Thursday the 24th of February at 3PM CET. She will talk about using neural networks to build surrogates for models with high-dimensional input spaces, I've included the abstract below. Hope to see you all there, Wouter Edeling 24 Feb. 2022 15h00 CET: Laura Scarabosio (Radboud University): Deep neural network surrogates for transmission problems with geometric uncertainties We consider the point evaluation of the solution to interface problems with geometric uncertainties, where the uncertainty in the obstacle is described by a high-dimensional parameter, as a prototypical example of non-smooth dependence of a quantity of interest on the parameter. We focus in particular on an elliptic interface problem and a Helmholtz transmission problem. The non-smooth parameter dependence poses a challenge when one is interested in building surrogates. In this talk we propose to use deep neural networks for this purpose. We provide a theoretical justification for why we expect neural networks to provide good surrogates. Furthermore, we present numerical experiments showing their good performance in practice. We observe in particular that neural networks do not suffer from the curse of dimensionality, and we study the dependence of the error on the number of point evaluations (which coincides with the number of discontinuities in the parameter space), as well as on several modeling parameters, such as the contrast between the two materials and, for the Helmholtz transmission problem, the wavenumber. Topic: CWI UQ+ML seminar Laura Scarabosio Time: Feb 24, 2022 03:00 PM Amsterdam Join Zoom Meeting https://cwi-nl.zoom.us/j/83713124696?pwd=UWJTbFBTc1FUZGxYbUNIRzlSbDZZZz09 Meeting ID: 837 1312 4696 Passcode: 432651

1 0

Fully funded PhD position at the U. of Groningen
by Michael Biehl 10 Feb '22

10 Feb '22

*Not quite three weeks left to apply! * A *fully funded PhD position* (4 years) in the *Statistical **Physics of Neural Networks* is available at the University of Groningen, The Netherlands, see https://www.rug.nl/about-ug/work-with-us/job-opportunities/?details=00347-0… for details and application details. Applications *(before March 1)* are only possible through this webpage. The title of the project is "The role of the activation function for feedforward learning systems (RAFFLES)". For further information please contact Michael Biehl. -- ---------------------------------------------------------- Prof. Dr. Michael Biehl Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence P.O. Box 407, 9700 AK Groningen The Netherlands Tel. +31 50 363 3997 https://www.cs.rug.nl/~biehl m.biehl(a)rug.nl

1 0

prediction modeling for hip OA, Ph.D. student
by Marco Loog 07 Feb '22

07 Feb '22

Ph.D. student vacancy in prediction modeling using artificial intelligence for hip osteoarthritis with Erasmus MC [EMC] and Delft University of Technology [TU Delft]. See the vacancy text for details: https://www.werkenbijerasmusmc.nl/en/vacancy/64984/phd-student-project-hips…

1 0

2024

2023

2022

2021

2020

Machine-learning-nederland February 2022