Anima Anandkumar: Enabling Zero-Shot Generalization in AI4Science | IACS Distinguished Lecturer
Anima Anandkumar
Bren professor at Caltech Computing + Mathematical Sciences Department
Director of machine learning research at NVIDIA
ABSTRACT: Many scientific applications heavily rely on the use of brute-force numerical methods performed on high-performance computing (HPC) infrastructure. Can artificial intelligence (AI) methods augment or even entirely replace these brute-force calculations to obtain significant speed-ups? Can we make groundbreaking new discoveries because of such speed-ups? However, such AI4science often requires zero-shot generalization to entirely new scenarios not seen during training. I will present exciting recent advances that build new foundations in AI that are applicable to a wide range of problems such as fluid dynamics and quantum chemistry. On the other side of the coin, the use of simulations to train AI models can be very effective in applications such as robotics and autonomous driving. Thus, we will see a convergence of AI, Simulations and HPC in the coming years.
Видео Anima Anandkumar: Enabling Zero-Shot Generalization in AI4Science | IACS Distinguished Lecturer канала Harvard Institute for Applied Computational Science
Bren professor at Caltech Computing + Mathematical Sciences Department
Director of machine learning research at NVIDIA
ABSTRACT: Many scientific applications heavily rely on the use of brute-force numerical methods performed on high-performance computing (HPC) infrastructure. Can artificial intelligence (AI) methods augment or even entirely replace these brute-force calculations to obtain significant speed-ups? Can we make groundbreaking new discoveries because of such speed-ups? However, such AI4science often requires zero-shot generalization to entirely new scenarios not seen during training. I will present exciting recent advances that build new foundations in AI that are applicable to a wide range of problems such as fluid dynamics and quantum chemistry. On the other side of the coin, the use of simulations to train AI models can be very effective in applications such as robotics and autonomous driving. Thus, we will see a convergence of AI, Simulations and HPC in the coming years.
Видео Anima Anandkumar: Enabling Zero-Shot Generalization in AI4Science | IACS Distinguished Lecturer канала Harvard Institute for Applied Computational Science
Показать
Комментарии отсутствуют
Информация о видео
12 июля 2022 г. 20:28:46
01:03:11
Другие видео канала
CS 109b: Data Science II: Advanced Topics in Data ScienceRayid Ghani: Doing Practical Data Science for Social Impact | IACS SeminarAlan Heavens: Cosmology with Weak Lensing | IACS SeminarCengiz Pehlevan: A Function Approximation of Perspective on Sensory Representations | IACS Seminar"Machine Learning for Partial Differential Equations" by Michael BrennerIsaac Lagaris: Neural Modeling and Differential Equations | IACS Seminar"Computational Biology in Translational Cancer Research"Susan Murphy: We used RL; but did it work? | IACS Distinguished Lecturer"Learning Quantum Emergence with AI" by Eun-Ah KimAlan Aspuru-Guzik: Billions and Billions of Molecules: Exploring Chemical Space | IACS SeminarGrushka-Cockayne: Forecasting Airport Transfer Passenger Flow Using Real-Time Data & Machine SeminarThore Graepel: Automatic Curricula in Deep Multi-Agent Reinforcement Learning | IACS SeminarVerena Kaynig: Connectomics - Mapping the Brain | IACS SeminarCSE Symposium: XY: Basketball Meets Big Data 1/24/2014Thomson Nguyen: Machine Learning for Small Business Lending | IACS SeminarScott Kuindersma: Controlling Multi-Contact Robot Behaviors with Optimization | IACS Seminar1/19 Hanna Halaburda- "Hopes and worries of blockchain commercial use”Emmanuel Candès: Recent Progress in Predictive Inference | IACS Distinguished LecturerKeynote Fernando Pérez | Jupyter Meets Earth: An Open, Collaborative Approach for Earth Data ScienceJessica Stauth: It’s Not Just Good Leadership Advice, It’s Good Data Science Practice | IACS SeminarWiDS 2022 Women of Color in Data Science