Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Employer
- University of Oslo
- Nanyang Technological University
- Harvard University
- National University of Singapore
- UNIVERSITY OF SOUTHAMPTON
- Humboldt-Universität zu Berlin
- INESC ID
- Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial
- Northeastern University
- SINGAPORE INSTITUTE OF TECHNOLOGY (SIT)
- University of Bergen
- University of Michigan
- Zintellect
- Łukasiewicz PORT
- Barnard College
- Center for Drug Evaluation and Research (CDER)
- Christian-Albrechts-Universitaet zu Kiel
- FCiências.ID
- George Mason University
- Hong Kong Polytechnic University
- Instituto de Investigação e Inovação em Saúde da Universidade do Porto (i3S)
- King Abdullah University of Science and Technology
- NOVA.id.FCT- Associação para a Inovação de Desenvolvimento da FCT
- Ryerson University
- SUNY University at Buffalo
- SciLifeLab
- Singapore University of Technology & Design
- The University of Memphis
- University of Agder
- University of Birmingham
- University of Birmingham;
- University of British Columbia
- University of Leeds
- University of Nottingham
- University of Texas at Austin
- 25 more »
- « less
-
Field
-
of nonlinear optics through the integration of artificial intelligence. The successful candidate will lead projects that combine the development of Physics-Informed Neural Networks (PINNs) with advanced fiber
-
who are interested in these or related fields, particularly those who may bring a new technology or perspective to bear on the work in the lab. Familiarity with neural networks and/or primate
-
develop numerical models and Machine Learning and AI methodologies, including Physics Informed Neural Networks (PINNs) and Symbolic Regression tools, to predict chemical reactions, impurity evolution along
-
). The position is subject to financing by the University of Bergen. About the project/work tasks Geometric Deep Learning (GDL) is a branch of machine learning that develops neural network models by explicitly
-
within a Research Infrastructure? No Offer Description Work Plan Study and application of methods for extracting understandable concepts and inducing logic-based theories from neural networks. Study of
-
, including deep neural networks and physics-informed neural networks, to analyse large datasets from gyrokinetic and fluid simulations of plasma turbulence Develop and train reduced-order models that capture
-
, Training or work experience in medical imaging, digital image processing, computer vision, pattern recognition, artificial intelligence, machine learning, deep neural networks, and statistics, Hands
-
neurophysiological experiments - mathematical analysis of the dynamics of neural networks - programming and numerical simulations of neural networks - development of quantitative model predictions and
-
transfer, fluid–solid interactions, and pressure drop in complex thermal structures. Design and train physics-guided surrogate models (e.g. neural networks with embedded physical constraints) for rapid
-
, such as, geometric/topological/algebraic data analysis, geometric/topological deep learning, Math for AI, categorical deep learning, sheaf neural networks, PINN/KAN models, neural operators, etc, and