This is why Deep Learning is really weird.
1:00:55
Transformers Need Glasses!
1:39:39
Neural and Non-Neural AI, Reasoning, Transformers, and LSTMs
18:09
The Genius of DeepSeek’s 57X Efficiency Boost [MLA]
23:46
Gradient Descent vs Evolution | How Neural Networks Learn
1:53:12
The Elegant Math Behind Machine Learning
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
1:09:26
MIT Introduction to Deep Learning | 6.S191
33:37