Plays via YouTube's privacy-enhanced embed

Building Brains to Understand the World's Data

Name: Building Brains to Understand the World's Data
Description: 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.

Google TechTalks

56 videos recommended on HN

YouTube

1 HN user recommended this talk1 month2013–2017 score 1

Years with an HN recommendation, 2007–2026

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

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.

“he gets into his ideas about the structure of the brain, and what he's done to reconstruct it in software/hardware.” (HN, 2013)

1 recommendations · 2 citations · Talks · intermediate · partly dated

Neuroscience & the brain Machine learning & deep learning Talks Life Sciences, Mind & Health

3 Hacker News comments

From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.

@scotth Jun 2013 Recommends

on HN thread Palm founder Jeff Hawkins on neurology, big data, and the future of AI

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]

Hawkins on brain structure and reconstructing it in software and hardware.

View on Hacker News

Citations, criticism and jokes

@dsego Feb 2014 Cites it

on HN thread The Stupidity of Computers

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

Offered as relevant talk on building brains.

View on Hacker News

@daveguy Oct 2017 Cites it

on HN thread A Theory of Sequence Memory in Neocortex

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

Hawkins' summary of what intelligence requires.

View on Hacker News