Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI

Rajesh P. N. Rao, Vishwas Sathish, Linxing Preston Jiang +2

The phenomenal advances in large language models (LLMs) and other foundation models over the past few years have been based on optimizing large-scale transformer models on the surp…