Revising Worldviews
Revising our beliefs can be a localized process, allowing for specific tweaks without overhauling our entire worldview. However, when it comes to neural networks, modifying even a small aspect requires retraining from scratch, highlighting the complexities of the frame problem. The shift from explicit to implicit competence in learning allows these systems to discern relevance more effectively, making them significantly more capable in handling complex relationships.In this clip
From this podcast
The Gradient
Pete Wolfendale: The Revenge of Reason
Related Questions
Why are neural networks hard to explain in the context of the episode Stephen Wolfram: ChatGPT and the Nature of Truth, Reality & Computation | Lex Fridman Podcast #376 and the clip Neural Nets and Symbolism?
Why are neural networks hard to explain in the context of the episode Stephen Wolfram: ChatGPT and the Nature of Truth, Reality & Computation | Lex Fridman Podcast #376 and the clip Neural Nets and Symbolism?
Can neural networks be explained?