Chapter
The Importance of Creating Admissible Sets of Functions in Deep Learning
28:58 - 35:26 (06:27)
Deep learning methods can create admissible sets of functions with significantly less training data. However, it is important to recognize that not all problems can be solved through deep learning and that the creation of admissible sets of functions requires sufficient training data.
Clips
Deep learning methods using deep neural networks can effectively solve problems while requiring significantly less training data.
28:58 - 31:40 (02:41)
Summary
Deep learning methods using deep neural networks can effectively solve problems while requiring significantly less training data. Additionally, the creation of deep architecture allows for the creation of an admissible set of functions based on the available training data.
ChapterThe Importance of Creating Admissible Sets of Functions in Deep Learning
EpisodeVladimir Vapnik: Statistical Learning
PodcastLex Fridman Podcast
The podcast discusses the classification of algorithms by worst-case running time in relation to their input, and poses the question of whether our models of intelligence are limited by our internal understanding of them.
31:40 - 33:57 (02:16)
Summary
The podcast discusses the classification of algorithms by worst-case running time in relation to their input, and poses the question of whether our models of intelligence are limited by our internal understanding of them.
ChapterThe Importance of Creating Admissible Sets of Functions in Deep Learning
EpisodeVladimir Vapnik: Statistical Learning
PodcastLex Fridman Podcast
The podcast host discusses complexity and worst-case scenarios with the guest, who believes that the concept of complexity is necessary in multi-medical tools for clear understanding and description.
33:57 - 35:26 (01:29)
Summary
The podcast host discusses complexity and worst-case scenarios with the guest, who believes that the concept of complexity is necessary in multi-medical tools for clear understanding and description.