Chapter
Converging Towards a Desired Function
18:32 - 27:25 (08:52)
This episode discusses selecting a set of admissible functions that give the same value with a chosen predicate, converging towards a desired function, and minimizing the square difference between functions to find the desired function.
Clips
The podcast discusses the concept of symmetry and the degree to which it can be applied in decision rule-making.
18:32 - 21:26 (02:53)
Summary
The podcast discusses the concept of symmetry and the degree to which it can be applied in decision rule-making. The question of whether symmetry is part of a hierarchical set of concepts or independent predicates is also explored.
ChapterConverging Towards a Desired Function
EpisodeVladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence
PodcastLex Fridman Podcast
In classification tasks, strong convergence refers to selecting a subset of functions that satisfy a specific property or criterion based on training data.
21:26 - 23:41 (02:15)
Summary
In classification tasks, strong convergence refers to selecting a subset of functions that satisfy a specific property or criterion based on training data. This subset is chosen by averaging the property of the training data and considering only functions of conditional probability that maintain this property.
ChapterConverging Towards a Desired Function
EpisodeVladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence
PodcastLex Fridman Podcast
The concept of admissible sets of functions is explained by taking the inner products of a function with another function and selecting a set of functions that is admissible with a specific predicate.
23:41 - 27:25 (03:43)
Summary
The concept of admissible sets of functions is explained by taking the inner products of a function with another function and selecting a set of functions that is admissible with a specific predicate. The idea of convergence is explored by looking at the square difference between two functions.