BI 120 James Fitzgerald, Andrew Saxe, Weinan Sun: Optimizing Memories
Brain Inspired
00:00
Optimal Generalization in Memory Research
The framework is built directly off of de lerning theory and double descent phenomena. There's an optimal amount of training time that you can train from a fixed batch of data, because otherwise you start picking up on these aspects that are just noise. As the ity of the rule that you're trying to learn increases, you can train for longer and longer. And so your your memory error is decreasing. That means more of the memory would transfer into ner cortex and not just begin the notebook.
Transcript
Play full episode
