Chapter
Clips
This podcast discusses how language is limited in its ability to express certain functions, such as geometric functions, which can be approximated through neural networks but not efficiently expressed through grammatical language.
1:04:18 - 1:06:12 (01:53)
Summary
This podcast discusses how language is limited in its ability to express certain functions, such as geometric functions, which can be approximated through neural networks but not efficiently expressed through grammatical language.
ChapterThe Brain as a Meta Learning System
Episode#101 – Joscha Bach: Artificial Consciousness and the Nature of Reality
PodcastLex Fridman Podcast
The Restricted Boltzmann Machine is a type of Boltzmann Machine that only has input and output layer, which makes the training and settling to its state much easier, compared to the regular Boltzmann Machine.
1:06:12 - 1:09:06 (02:53)
Summary
The Restricted Boltzmann Machine is a type of Boltzmann Machine that only has input and output layer, which makes the training and settling to its state much easier, compared to the regular Boltzmann Machine.
ChapterThe Brain as a Meta Learning System
Episode#101 – Joscha Bach: Artificial Consciousness and the Nature of Reality
PodcastLex Fridman Podcast
The brain is thought to be a meta learning system which discovers algorithms to solve complex problems.
1:09:06 - 1:13:03 (03:56)
Summary
The brain is thought to be a meta learning system which discovers algorithms to solve complex problems. Reinforcement learning agents play a key role in this system.