Building Brains to Understand the World's Data
Google TechTalks1 HN recommenders · 2013–2017
84K views · talk · dated · Uploaded 2013-03-11
Jeff Hawkins presents his view that the neocortex works on principles different from traditional computers. He describes sparse distributed representations and how they are learned, then shows how Numenta applies them to predict from high-velocity data streams.
Recommended as Hawkins' own accessible statement of his brain-inspired theory of intelligence and its software implementation.
2:25:52The spelled-out intro to neural networks and backpropagation: building micrograd
Andrej Karpathy
57:151. Introduction to Human Behavioral Biology
Stanford
18:40But what is a neural network? | Deep learning chapter 1
3Blue1Brown
52:29Stanford's Sapolsky On Depression in U.S. (Full Lecture)
Stanford
52:07What Bodies Think About: Bioelectric Computation Outside the Nervous System - NeurIPS 2018
The Artificial Intelligence Channel
1:30:28AlphaGo - The Movie | Full award-winning documentary
Google DeepMind
16:29The great porn experiment | Gary Wilson | TEDxGlasgow
TEDx Talks
27:14Transformers, the tech behind LLMs | Deep Learning Chapter 5
3Blue1Brown
3 comments from Hacker News
Here's an related talk by Jeff Hawkins at Google, where he gets into his ideas about the structure of the brain, and what he's done to reconstruct it in software/hardware. [VIDEO]
What about this? Building Brains to Understand the World's Data (google tech talk): [VIDEO] The result is [LINK]
I think that Hawkins has a great summary on some things that are necessary for intelligence [0]. Personally I think the tie between motor actuation and sensory detection is one of the most important -- did a project on that in 2010. Motor-sensory link is essentially how all intelligence evolved. Even c.elegans has neurons to determine whether it should wiggle one way or another. On the surface he seems to be cramming a whole lot of "solutions" into his HTM (hierarchical temporal memory). HTM is an interesting implementation and the sparse coding is definitely a benefit. However I think he is focused too much on his baby and not on other techniques that may fulfill the necessary components more efficiently. That is just on the surface. With a product / research balance maybe we just aren't seeing all the cool things going on underneath in research, but it does seem like that research will be shoe-horned into HTM whether or not it is the best architecture. [0] [VIDEO] Starting at ~8m20s