Published Jul 21, 2020
Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386 (Video)
Pavan Turaga delves into the convergence of physics-based constraints and geometric principles to tackle data scarcity in deep learning, enhancing AI model robustness and exploring the potentials and limitations of one-shot learning.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386
Answers 383 questions
Geometric Deep Learning with Joan Bruna & Michael Bronstein - #90
Answers 383 questions
Deep Learning, Transformers, and the Consequences of Scale with Oriol Vinyals - #546
Answers 383 questions
Deep Learning in Optics with Aydogan Ozcan - TWiML Talk #237
Answers 383 questions
Engineering a Less Artificial Intelligence with Andreas Tolias - #379
Answers 383 questions
Deep Neural Nets for Visual Recognition with Matt Zeiler - #22
Answers 383 questions
Deep Learning: Modular in Theory, Inflexible in Practice with Diogo Almeida - #8
Answers 383 questions
Transformers for Tabular Data at Capital One with Bayan Bruss - #591
Answers 383 questions
Composing Graphical Models With Neural Networks, w/ David Duvenaud - #96
Answers 383 questions
Learning to Ponder: Memory in Deep Neural Networks - #528
Answers 383 questions
Deep Robotic Learning with Sergey Levine - #37
Answers 383 questions
Trends in Computer Vision with Siddha Ganju - TWiML Talk #218
Answers 383 questions
Inverse Programming for Deeper AI with Zenna Tavares, w/ Zenna Tavares - #114
Answers 383 questionsEmbedded Deep Learning at Deep Vision with Siddha Ganju - #95
Answers 383 questions
Deep Learning for Live-Cell Imaging with David Van Valen - #141
Answers 383 questions