AI & ML·Public Colloquium·Mechanistic Interpretability, Alignment & World Models · Geoffrey Hinton · Association for Computing Machinery (ACM)
32:28
Academic Discipline
AI & Machine Learning
Deep learning, language models, reinforcement learning, statistical learning theory, representation learning, and vision.
10courses86standalone talks213total lectures
Subfields
Deep Learning— Neural network architectures, backpropagation, automatic differentiation, diffusion and generative models.
7 topicsjknavigate↵watchcchaptersssavexwatched
Save
54:33
59:10
39:55
38:10
Neural Networks: Zero to Hero · Lec 5·Mechanistic Interpretability, Alignment & World Models · Andrej Karpathy · Independent / Eureka Labs
1:55:24
45:57
Convolutional Neural Networks for Visual Recognition · Lec 16·Computer Vision & Graphics · Ian Goodfellow · Stanford University
1:21:46
CS 156 · Learning From Data · Lec 10·Mechanistic Interpretability, Alignment & World Models · Yaser Abu-Mostafa · Caltech
1:25:16
Showing 10 of 10 lectures10.5h shown