Chapter
Handwritten Recognition vs Language models: A Comparison
1:06:50 - 1:13:55 (07:04)
The limitations of handwritten recognition and natural language processing are discussed in this podcast, with a comparison made between language models which have a finite set of letters and simpler benchmarks and image analysis which needs more complicated and sophisticated approaches. The role of symmetry is also highlighted in real-life 2D images.
Clips
The speaker discusses the relationship between handwritten recognition and language in regards to general intelligence, questioning the extent to which the two are applicable to the broader problem.
1:06:50 - 1:11:02 (04:11)
Summary
The speaker discusses the relationship between handwritten recognition and language in regards to general intelligence, questioning the extent to which the two are applicable to the broader problem. Additionally, they consider the importance of human language in expressing ideas.
ChapterHandwritten Recognition vs Language models: A Comparison
EpisodeVladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence
PodcastLex Fridman Podcast
While natural language processing has benchmarks from simple tasks like understanding sentences to complex dialogue, vision science is still struggling to properly recognize symbols and handwriting, and needs to move towards understanding the physical environment like babies do.
1:11:03 - 1:13:55 (02:52)
Summary
While natural language processing has benchmarks from simple tasks like understanding sentences to complex dialogue, vision science is still struggling to properly recognize symbols and handwriting, and needs to move towards understanding the physical environment like babies do.