Episode 11: Vincent Sitzmann, MIT, on neural scene representations for computer vision and more general AI
Generally Intelligent
Navigating Perception and Neural Networks
This chapter explores the intricacies of human perception and its implications for neural networks, emphasizing how both rely on approximations rather than perfect representations. The speakers discuss advancements in neural network training, including contrastive objectives and self-supervised learning, highlighting the potential for more flexible and intelligent models.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
