Discrete Program Synthesis
The discussion delves into the concept of generalization in machine learning, contrasting discrete program synthesis with traditional neural networks. Sreejan highlights that while different systems have unique inductive biases, intelligence spans a broad spectrum, with discrete domains like planning and arithmetic being areas where symbolic algorithms excel. The conversation emphasizes the importance of understanding both program induction and neural network approaches to grasp the full landscape of artificial intelligence.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#97 SREEJAN KUMAR - Human Inductive Biases in Machines from Language
Related Questions