Learning vs. Reasoning
Ishan explores the distinction between learning and reasoning, emphasizing that while neural networks excel at recognition, they struggle with complex reasoning tasks. He highlights the challenges of generalization in machine learning, noting that current models often fail to predict their performance on unseen scenarios. The conversation delves into the potential of program synthesis and the learnability of reasoning, suggesting that understanding how machines can build upon basic concepts is crucial for advancement.In this clip
From this podcast
Lex Fridman Podcast
Ishan Misra: Self-Supervised Deep Learning in Computer Vision | Lex Fridman Podcast #206
Related Questions
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?
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?
How do neural networks demonstrate reasoning capabilities as discussed in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Neural Networks and Reasoning?