Zico Kolter - Incorporating physics and decision making into deep learning via implicit layers
Talk starts at 2:57
Prof. Zico Kolter from Carnegie Mellon speaking in the Data-driven methods for science and engineering seminar on January 22, 2021.
For more information including past and upcoming talks, visit: http://www.databookuw.com/seminars/
Sign up for notifications of future talks: https://mailman11.u.washington.edu/mailman/listinfo/datadriven-seminar
Links:
https://zicokolter.com/
http://implicit-layers-tutorial.org/
Abstract: Despite their wide applicability, deep networks often fail to exactly capture simple "known" features of real-world data sets, such as those governed by physical laws. In this talk, I'll present methods for integrating hard constraints, such as those associated with decision making, optimization problems, or physical simulation, directly into the predictions of a deep network. Our tool for achieving this will be the use of so-called implicit layers in deep models: layers that are defined implicitly in terms of conditions we would like them to satisfy, rather than via an explicit computation graph. I'll discuss how we can use these layers to embed (exact) physical constraints, robust control criteria, and task-based objectives, all within the framework of traditional deep learning. I will highlight several applications of this work in reinforcement learning, control, energy systems, and other settings, and discuss generalizations and directions for future work in the area.
Видео Zico Kolter - Incorporating physics and decision making into deep learning via implicit layers канала Physics Informed Machine Learning
Prof. Zico Kolter from Carnegie Mellon speaking in the Data-driven methods for science and engineering seminar on January 22, 2021.
For more information including past and upcoming talks, visit: http://www.databookuw.com/seminars/
Sign up for notifications of future talks: https://mailman11.u.washington.edu/mailman/listinfo/datadriven-seminar
Links:
https://zicokolter.com/
http://implicit-layers-tutorial.org/
Abstract: Despite their wide applicability, deep networks often fail to exactly capture simple "known" features of real-world data sets, such as those governed by physical laws. In this talk, I'll present methods for integrating hard constraints, such as those associated with decision making, optimization problems, or physical simulation, directly into the predictions of a deep network. Our tool for achieving this will be the use of so-called implicit layers in deep models: layers that are defined implicitly in terms of conditions we would like them to satisfy, rather than via an explicit computation graph. I'll discuss how we can use these layers to embed (exact) physical constraints, robust control criteria, and task-based objectives, all within the framework of traditional deep learning. I will highlight several applications of this work in reinforcement learning, control, energy systems, and other settings, and discuss generalizations and directions for future work in the area.
Видео Zico Kolter - Incorporating physics and decision making into deep learning via implicit layers канала Physics Informed Machine Learning
Показать
Комментарии отсутствуют
Информация о видео
23 января 2021 г. 0:10:44
01:18:47
Другие видео канала
NeurIPS 2020 Tutorial: Deep Implicit LayersZico Kolter: "Fast semidefinite programming for (differentiable) combinatorial optimization"Scientific Machine Learning: Where Physics-based Modeling Meets Data-driven LearningDeep equilibrium models via monotone operators - Zico KolterDeep Learning in Bioinformatics | Recent AdvancementZico Kolter (Carnegie Mellon University): "Cheating with neural networks"Zico Kolter: "Integrating optimization, constraints, and control within deep learning models"Simulation: The Challenge for Data Sciencecomputer vision deep learning railway sign detectionNeural Ordinary Differential Equations - Best Paper Awards NeurIPS 2018Physics-based machine learning for atomistic modellingIntegrating Constraints into Deep Learning Architectures with Structured LayersDeep Learning CarsQuantum Physics for 7 Year Olds | Dominic Walliman | TEDxEastVanBuilding a Custom Environment for Deep Reinforcement Learning with OpenAI Gym and PythonOn Evaluating Adversarial RobustnessA Hands-on Introduction to Physics-informed Machine LearningLiquid Neural NetworksZico Kolter (CMU) -- Making Deep Learning more Robust, Modular, and EfficientDeep Learning for Decision Making and Control