- Machine-learning-nederland

CWI seminar
by Wouter Edeling 22 Mar '21

22 Mar '21

Dear all, This Thursday (the 25th) at 15h00 we will have the next speaker in our seminar on Machine Learning and Uncertainty Quantification for Scientific Computing. Jurriaan Buist will talk about closure modelling for pipe flows using neural networks. You can find the zoom link and the abstract below. Best regards, Wouter Edeling Join Zoom Meeting https://cwi-nl.zoom.us/j/86539157750?pwd=aUZld01lY0pFQXZBM20vcDgxa3hFQT09 Meeting ID: 865 3915 7750 Passcode: 573238 25 Mar. 2021 15h00: Jurriaan Buist (CWI): Energy conservation for the one-dimensional two-fluid model for two-phase pipe flow The one-dimensional two-fluid model (TFM) is a simplified model for multiphase flow in pipes. It is derived from a spatial averaging process, which introduces a closure problem concerning the wall and interface friction terms, similar to the closure problem in turbulence. To tackle this closure problem, we have approximated the friction terms by neural networks trained on data from DNS simulations. Besides the closure problem, the two-fluid model has a long-standing stability issue: it is only conditionally well-posed. In order to tackle this issue, we analyze the underlying structure of the TFM in terms of the energy behavior. We show the new result that energy is an inherent 'secondary' conserved property of the mass and momentum conservation equations of the model. Furthermore, we develop a new spatial discretization that exactly conserves this energy in simulations. The importance of structure preservation, and the core of our analysis, is not limited to the TFM. Neural networks that approximate physical systems can also be designed to preserve the underlying structure of a PDE. In this way, physics-informed machine learning can yield more physical results.

1 0

Senior Bioinformatician - AstraZeneca (Cambridge, UK)
by Sergio Martinez Cuesta 13 Mar '21

13 Mar '21

*Are you a quantitatively-minded scientist looking to apply bioinformatics and machine learning to design the next generation of therapeutics? Do you wish to join a growing team where you will have the possibility to further exploit our drug discovery platforms? If yes, we have the position for you at AstraZeneca in Cambridge!* We are currently looking for a Senior Bioinformatician to join us at AstraZeneca in Cambridge, UK as part of the Data Sciences and Quantitative Biology team in biopharma R&D: https://careers.astrazeneca.com/job/cambridge/senior-bioinformatician-data-… Deadline for applications *23rd March*! Please distribute with bioinformatics colleagues reaching their ends of contracts. Best wishes, Sergio

1 0

vacancy PhD student Ghent University
by Stijn Luca 09 Mar '21

09 Mar '21

Dear all, A vacancy for an assistant is available at our department (Data Analysis and Mathematical Modelling) of Ghent University with a 50% research / 50% teaching assignment. People with a strong background in data analysis and statistics are encouraged to apply. Deadline for application is 18-03-2021. For more info and the application procedure, click here<https://career012.successfactors.eu/career?company=C0000956575P&career_job_…>. [cid:image001.jpg@01D714C7.57A6B6F0]<https://www.ugent.be/bw/nl/faculteit/100> Prof. dr. Stijn Luca Assistant professor T +32 9 264 59 34 Department Data Analysis and Mathematical Modelling Research Unit BIOSTAT: Biostatistics www.biostat.ugent.be<http://www.biostat.ugent.be> Campus Coupure, Block A 1st floor 110.068, Coupure links 653, B-9000 Ghent, Belgium directions<https://www.google.com/maps/dir/Coupure+Links+653,+9000+Gent/@51.0527795,3.…> T administration office +32 9 264 59 32 www.ugent.be<https://www.ugent.be/bw/en> e-maildisclaimer<https://helpdesk.ugent.be/e-maildisclaimer.php>

1 0

NeurIPS Debriefing 2020 - Reminder and Schedule
by Jack Mayo 04 Mar '21

04 Mar '21

Dear Dutch Machine Learners, Here's to reminding you all that the NeurIPS debriefing will take place at the following virtual location: Friday March 5, 2021 14h00-17h00 Via the Following Zoom link: https://uva-live.zoom.us/j/89293881695 The speakers and topics are: Mustafa Celikok, TU Delft - A Unifying View of Optimism in Episodic Reinforcement Learning by Gergely Neu, Ciara Pike-Burne Alexander Mey, TU Delft - Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes by Yi Tian, Jian Qian, Suvrit Sra Jack Mayo, University of Amsterdam - Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards by Kyungjae Lee, Hongjun Yang, Sungbin Lim, Songhwai Oh Alexander Ly, CWI - Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree by Peizhong Ju, Xiaojun Lin, Jia Liu In addition to the talks, we will also have a creative intermezzo, in which Peter van der Putten (Leiden University) will showcase a creative piece using the GPT3 playground that was part of the digital gallery of the NeurIPS Workshop on Machine Learning for Creativity and Design 2020. For up to date information and an overview of past meetings, see www.timvanerven.nl/neurips-debriefing/<https://eur04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.timvan…> Looking forward to seeing you there! Best regards, Jack Mayo and Tim van Erven

1 0

CWI seminar 11 March 15h30
by Wouter Edeling 04 Mar '21

04 Mar '21

Dear all, At CWI, we are organizing a seminar on Machine Learning and Uncertainty Quantification for Scientific Computing. Next Thursday (the 11th) at 15h30 we will have the next speaker. Benjamin Sanderse will talk about multi-level neural networks for partial differential equations with uncertain parameters. You can find the zoom link and the abstract below. We hold talks about twice a month, with both internal and external speakers. More information can be found here: https://www.cwi.nl/research/groups/scientific-computing/uq-seminar/seminar-…, which is updated regularly. Best regards, Wouter Edeling https://cwi-nl.zoom.us/j/9201774084?pwd=OFBqM1dUenFreGdPUWEwZFYvMlJ6UT09 11 Mar. 2021 15h30: Benjamin Sanderse (CWI): Multi-Level Neural Networks for PDEs with Uncertain Parameters A novel multi-level method for partial differential equations with uncertain parameters is proposed. The principle behind the method is that the error between grid levels in multi-level methods has a spatial structure that is by good approximation independent of the actual grid level. Our method learns this structure by employing a sequence of convolutional neural networks, that are well-suited to automatically detect local error features as latent quantities of the solution. Furthermore, by using the concept of transfer learning, the information of coarse grid levels is reused on fine grid levels in order to minimize the required number of samples on fine levels. The method outperforms state-of-the-art multi-level methods, especially in the case when complex PDEs (such as single-phase and free-surface flow problems) are concerned, or when high accuracy is required.

1 0

Two PhD positions in NLP and Speech at Tilburg University
by Grzegorz Chrupała 04 Mar '21

04 Mar '21

These positions are associated with the project “InDeep: Interpreting deep learning models for language, speech & music” in collaboration with several universities and companies in the Netherlands, funded by the Dutch Research Council (NWO). Each of the two PhD candidates will work on one the following subprojects: - Development and evaluation of general-purpose methods for interpretability (led Dr. Afra Alishahi). - Analysis and control techniques for deep-learning based speech processing models (led by Dr. Grzegorz Chrupała). Details: https://www.academictransfer.com/en/298252/two-phd-positions-in-nlp-and-spe… Further vacancies within the InDeep project are or will soon be available here: https://interpretingdl.github.io/vacancies Best regards, -- Grzegorz Chrupała Department of Cognitive Science and Artificial Intelligence Tilburg University PO Box 90153 5000 LE Tilburg The Netherlands Twitter: @gchrupala Web: grzegorz.chrupala.me Phone: +31 13 466 8020 Email: g.chrupala(a)uvt.nl

1 0

Postdoctoral position in bioinformatics at ULB Brussels
by Fabrizio Pucci 03 Mar '21

03 Mar '21

The Computational Biology and Bioinformatics group of the Brussels University (ULB) is seeking candidates for a postdoctoral position. *Research context*: The understanding of the biophysical mechanisms that drive single nucleobase substitutions in different regions of the human genome is one of the key questions of the post-genomic era. These mutations, whether inherited or somatic, are potentially responsible for a huge range of rare and complex diseases. The rationalization of these mechanisms is highly intricate, since base substitutions depend on the nucleotide sequence context and can be triggered by a wide range of physical, chemical or biological factors. *Objective*: In the AtOme project, we will bridge the gap between the atomic-level characterization of mutagenesis processes and the resulting phenotypic traits. More specifically, we will investigate the role of DNA charge transport in mutational and pathogenic processes using a multiscale computational approach combining quantum chemistry, machine learning and genomics. *Offer*: A full time postdoctoral position for 2 years. Flexible starting date, between now and October 2021. Possibility of extension through an FNRS postdoctoral research grant or a Marie Curie EC grant. *Required:* - PhD degree in Sciences (Bioinformatics, Bioengineer, Physics, Chemistry, Informatics). - Excellent programming skills. - Excellent publication record. - Maximum 6 years research experience after PhD. - International mobility (maximum 24 months of residence in Belgium in the last 3 years). *Desirable:* - Experience in the area of quantum chemistry, machine learning, and/or genome bioinformatics. *Contact*: Please submit: (1) a cover letter detailing your background and interest in the position, (2) a full CV and (3) two references (with name, email, address, phone number), to M. Rooman (mrooman(a)ulb.ac.be). *Application deadline: *June 1, 2021

1 0

Tenure Track Assistant/Associate Professor Modelling and AI for Systems Medicine
by Riel, Natal van 01 Mar '21

01 Mar '21

We have a vacancy: Tenure Track Assistant/Associate Professor Modelling and AI for Systems Medicine at Eindhoven University of Technology https://jobs.tue.nl/en/vacancy/tenure-track-assistant-associate-professor-m… . We are looking for a creative and pro-active team player to initiate a new research line in biomedical systems biology. We unite data-driven and model-based approaches for biomedical research, engineering and healthcare. We search for candidates with a PhD degree in computational biology, biomedical engineering or other relevant disciplines. New directions could be the development and application of AI technology for learning and adaptation of dynamic models. This may enable the creation of ‘digital twins’ and contribute to personalized health and precision medicine. We search for candidates that want to play a leading role in this rapidly developing field. The TU/e provides an exciting ecosystem for healthcare engineering research and innovation, which includes close collaboration with local hospitals, industry and the cross-departmental artificial intelligence institute EAISI (www.tue.nl/ai<http://www.tue.nl/ai>). We offer a substantial start-up package to kick-off your career. Deadline for applications: 30/04/2021. Kind regards, Natal van Riel Prof. dr. ir. Natal A.W. van Riel [cid:image005.png@01D70EEF.4DC1FB50] Professor of Biomedical Systems Biology Head of Systems Biology and Metabolic Disease (SBMD) Computational Biology group Department of Biomedical Engineering Eindhoven University of Technology P.O. Box 513, 5600 MB Eindhoven, The Netherlands Internal address: Building Gemini-Zuid 3.109 Groene Loper, 5612 AZ Eindhoven route and map<http://www.tue.nl/en/our-university/departments/biomedical-engineering/the-…> T +31 40 247 5506 (5537) n.a.w.v.riel(a)tue.nl<mailto:n.a.w.v.riel@tue.nl> www.tue.nl/en/research/researchers/natal-van-riel/<https://www.tue.nl/en/research/researchers/natal-van-riel/> | www.tue.nl/cbio [cid:image006.png@01D70EEF.4DC1FB50] Professor of Computational Modelling Amsterdam University Medical Centers University of Amsterdam n.a.vanriel(a)amsterdamumc.nl<mailto:n.a.vanriel@amsterdamumc.nl>

1 0

Professor Position Artificial Intelligence For Industry (KU Leuven, Belgium)
by Peter Karsmakers 01 Mar '21

01 Mar '21

Dear Colleagues, KU Leuven has a fixed-term (5 year) part-time (95%) academic vacancy in the area of Artificial Intelligence at its campus in Bruges. We are looking for internationally oriented candidates with an excellent research record, preferably focused on deploying AI in Business and Industrial Environments, and with demonstrable didactical skills. The expected start date is October 1, 2021. The successful applicant will be appointed in the Faculty of Engineering Technology. This Faculty is part of the Science, Engineering and Technology Group of KU Leuven. The position is interdepartmental, with a joint appointment in both the Department of Computer Science and the Department of Electrical Engineering (ESAT). The successful applicant will engage in collaborations with experts in data analysis and AI and academic users of AI technology in the broader region. Overall, he/she will be an active member of the KU Leuven Institute for Artificial Intelligence (Leuven.ai). This interdisciplinary institute combines the AI expertise of 60+ professors, 100s of researchers and 500 master students. As one of the 10 most innovative universities in the world, KU Leuven has been very successful in the creation of spin-off companies, illustrating the socio-economic relevance of its research. Many of these spin-off companies are technology leaders within their domain, and their products and services are renowned internationally. More information see: https://www.kuleuven.be/personeel/jobsite/jobs/56002799?hl=en&lang=en Best regards, Peter — prof. dr. Peter Karsmakers [signature_1523137006] [/var/folders/z8/hsb0l6j16bsg031x1w8zq02r0000gn/T/com.microsoft.Outlook/WebArchiveCopyPasteTempFiles/image][page1image8119648] KU Leuven | Faculty of Engineering Technology Geel Campus | Kleinhoefstraat 4, 2440 Geel (Belgium) tel. +32 14 72 13 58 | www.iiw.kuleuven.be/geel<http://www.iiw.kuleuven.be/geel> Departement of Computer Science | DTAI-ADVISE ADVISE<http://www.kuleuven.be/advise> - DTAI<https://dtai.cs.kuleuven.be/> [signature_756872295]

1 1

[jobs] 4 PhDs@TU Delft - Automated vehicles interacting with humans
by Jens Kober - 3ME 26 Feb '21

26 Feb '21

TU Delft is recruiting four PhD candidates to develop new computational approaches enabling automated vehicles to interact with the humans around them in a responsible and robust way: 1. Hybrid AI for Human Behavior Prediction: https://www.academictransfer.com/en/298180/phd-position-hybrid-ai-for-human… 2. Emergent Behavior and Responsibility in Mixed-traffic Interactions: https://www.academictransfer.com/en/298179/phd-position-emergent-behavior-a… 3. Learning and Control for Probabilistic Multi-Agent Systems: https://www.academictransfer.com/en/298195/phd-position-learning-and-contro… 4. Robustness and Control of Machine Learning Models: https://www.academictransfer.com/en/298194/phd-position-robustness-and-cont…

1 0

2024

2023

2022

2021

2020

Machine-learning-nederland