Skip to content
HHackerTube.videoSurprise me

Building Brains to Understand the World's Data

Building Brains to Understand the World's Data on HackerTube: recommended by 1 Hacker News commenter across 1 month, 2013–2017.

Google TechTalks

talk · intermediate · dated

Open on YouTube

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.

Why Hacker News recommends it

Recommended as Hawkins' own accessible statement of his brain-inspired theory of intelligence and its software implementation.

people recommended it
1
separate months
1
strong recommendations
0
discussed on HN
2013–2017
“he gets into his ideas about the structure of the brain, and what he's done to reconstruct it in software/hardware.”
— scotth, Jun 2013, in “Palm founder Jeff Hawkins on neurology, big data, and the future of AI”

What HN commenters said

3 Hacker News comments link this video. Each one links back to its thread.

scotthJun 2013Recommends

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. ▶ this video

in “Palm founder Jeff Hawkins on neurology, big data, and the future of AI” · View on HN

daveguyOct 2017Cites it

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] ▶ this video Starting at ~8m20s

in “A Theory of Sequence Memory in Neocortex” · View on HN

dsegoFeb 2014Cites it

What about this? Building Brains to Understand the World's Data (google tech talk): ▶ this video The result is [link]

in “The Stupidity of Computers” · View on HN

Topics & tags

Neuroscience & the brainMachine learning & deep learningjeff hawkinssparse distributed representationsnumentaneocortexprediction