Representation and Reasoning
Peter discusses the challenges of representation and reasoning in AI, highlighting the limitations of traditional symbolic approaches when faced with the complexities of the real world. He suggests that integrating more nuanced representations, such as word embeddings, could enhance understanding and application of reasoning strategies. Additionally, he raises the question of whether better data alone can improve explainability, or if elements of symbolic systems are necessary for clearer insights into AI decision-making.In this clip
From this podcast
Lex Fridman Podcast
Peter Norvig: Artificial Intelligence: A Modern Approach | Lex Fridman Podcast #42
Related Questions
What is the challenge around explainability in AI as discussed in the episode Peter Norvig: Artificial Intelligence: A Modern Approach | Lex Fridman Podcast #42 and the clip Representation and Reasoning?
Can neural networks be made to reason as discussed in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Neural Networks and Reasoning, in relation to the episode Peter Norvig: Artificial Intelligence: A Modern Approach | Lex Fridman Podcast #42 and the clip Deep Learning Insights?
Can neural networks be made to reason as discussed in the episode Peter Norvig: Artificial Intelligence: A Modern Approach | Lex Fridman Podcast #42 and the clip Deep Learning Insights, as well as in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Neural Networks and Reasoning?