Surrogate Models & Gradients
Tim explains how surrogate models can help optimize neural networks, while Tom discusses the limitations of training environments in machine learning. The discussion delves into using surrogate gradients in neuroscience and the impact of test environments on meta gradients.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#49 - Meta-Gradients in RL - Dr. Tom Zahavy (DeepMind)
Related Questions