Unifying Symbolic and Connectionist AI
Pedro highlights the power of logic programming in learning and reusing knowledge for complex inference, a capability lacking in connectionist AI. Tim emphasizes the need for dynamic knowledge acquisition and the creation of on-the-fly abstractions to enhance intelligence beyond crystallized human abstractions.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#96 Prof. PEDRO DOMINGOS - There are no infinities, utility functions, neurosymbolic
Related Questions
What is symbolic reasoning in the context of the episode Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics | Lex Fridman Podcast #15 and the clip Reasoning and Abstraction?
What are the practical applications of symbolic reasoning as discussed in the episode Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics | Lex Fridman Podcast #15 and the clip Reasoning and Abstraction?