more misc notes on the biological path to strong ai

agree that this is looking like the best path to strong AI. don't agree that the biological is the only potential path.

the biological path is only the best path while we share fundamental constraints with the brain.

SDRs are a great example of evolution solving a problem working against limiting constraints. In the the case of SDRs the constraints are those of computing power, storage space and access times in the brain.

The reliance on SDRs is likely linked to one of the bugs in our intelligence - the bias toward equivalence (the "IS A" bias). A hypothetical predictive system implemented without SDRs or with less dependence on SDRs might also be an intelligence that suffers less from the is-a bias.

octobrains

Did the 100s of smelling, tasting, feeling suckers on the 8 legs of an octopus do a similar thing for the octopus brain as the evolution of hands did to ours  ?... and did the decentralised architecture of the octopus brain reduce the impact the 8 arm rich information stream had on evolving a complex central brain?

Or was it that without the single repeated architecture of the mammalian neocortex as general intelligence engine, gains made in complexity in those sensory streams were not as reusable toward the evolution of a more general intelligence ??

principles of hierarchical-temporal-memory

HTMemory and Sparse Distributed Networks. Lots of progress in understanding the neocortex - how intelligence works in the brain - and modelling that for a cortical approach to machine intelligence

UPDATE: broken link: Video moved to http://numenta.com/learn/htm-videos-from-jeff-hawkins.html.

Direct link on youtube: https://youtu.be/6ufPpZDmPKA

a reminder - mindfulness training and the neuroscience supporting it

The secular practice of mindfulness training or meditation, and mindfulness based cognitive therapy has been gaining momentum in the mainstream for a while now... This google-tech-talk describing mindfulness training is old, but pretty useful, and it presents the (then preliminary) neuroscience supporting the practice nicely.

http://www.youtube.com/watch?v=peA6vy0D5Bg (an hour long google tech-talk by Matthieu Ricard)

Ricard is a buddhist monk who earned his PhD in molecular genetics at the Pasteur Institute before turning his attention to the practice and study of Tibetan Buddhism -- and worth suffering those opening jokes for.
 

(I've posted on him and this subject before - http://jaysenn.blogspot.com/2007/06/mindtraining.html)  

-----
here's more:

• http://www.diydharma.org/science-meditation-mattieu-ricard
• http://www.diydharma.org/audio/by/album/happiness
• http://www.matthieuricard.org/en/
• http://www.matthieuricard.org/en/medias/categories/meditation-and-mind-training

building intelligence

Jeff Hawkins again, this time in a googtechtalk. 1hr.  

Like in his earlier videos and book, he gives the best explanation of the neocortex i've heard so far --the neocortex is a hierarchical temporal memory system, implemented as a sparse distributed representation.

See earlier posts on this:
http://jaysenn.blogspot.com/2012/10/grokking-htm-for-ai.html
http://jaysenn.blogspot.com/2007/07/intelligence-is-prediction.html

grokking htm for ai

or .. Notes on Understanding Hierarchical Temporal Memory and its use in Artificial Intelligence and Knowledge Representation.

A few years ago I blogged about a TedTalk by Jeff Hawkins on how brain science will change computing. To summarize, the idea was that intelligence was more about prediction than behaviour, that the neocortex evolved to to basically be a mechanism to predict the future, and that it could be simply modeled as vast networks of hierarchical elements that predict their future input sequences - a hierarchical temporal memory (HTM) system.
Importantly, rather than the much more difficult task of modeling the entire brain, including the ancient and incredibly complex areas below the neocortex that deal with things like emotions and behaviours, one could approximate intelligent behaviour by modeling the much simpler cortex as a HTM - with simple repeated structure and algorithm.

Here's an update with more from Jeff Hawkins, and HTM ..

The following links are for a 2008 talk given by him on AI.. give it a watch
Jeff Hawkins on Artificial Intelligence - Part 1/5
Jeff Hawkins on Artificial Intelligence - Part 2/5
Jeff Hawkins on Artificial Intelligence - Part 3/5
Jeff Hawkins on Artificial Intelligence - Part 4/5

Jeff Hawkins on Artificial Intelligence - Part 5/5

..some notes from the above:
- Work started by looking at what the structure of the brain could tell us about memory/knowledge storage.
- Memory - the bottom is close to the sensory system - retina for visual system, skin for touch, ears .. etc.
- Top nodes in the hierarchy get assigned to specific concepts/objects - like the individual neurons that fire every time you see or imagine Tupac and only Tupac (true story) 
- All nodes in the hierarchy are basically the same, and they all ..
    - look for temporal and spatial patterns/sequence
    - and pass the name of the recognized sequence up
    - pass the predictions they make down the hierarchy
- You get fast changing patterns at the bottom, slower changing as you move up the hierarchy.
- After training an HTM system (in silicon or neurons), you get something that learns hierarchical models of causes (statistical regularity) in the world - using bayesian techniques to build a belief propagation network.
- HTM's make the assumption that the world is hierarchical
- Predicting what can come from htm:
   - we cant, but ..
   - it could be much faster - neurons are slow
   - it could have other architectures - bigger bottom layers, fueled by big-data for example, or from large sensory arrays, etc. 

The latest thing I've come across from Hawkins' company Numenta, is their new Grok system (love the Heinlein reference). Grok is a cloud-based prediction engine that finds complex patterns in data streams and generates actionable predictions in real time. Check it out on Numenta's site, and their tech page
...
(more to follow.. soonish)

Blue Brain Project : Year One

just finished watching this preview of a documentary film on the BlueBrain Project - an attempt to reverse-engineer a human brain.

catch it here at The Beautiful Brain

the project site is at http://bluebrain.epfl.ch/

a good brain theory?

slightly annoying, but sharp..


i liked the bit about intelligence having more to do with predictive power than it does behavior .. Maybe if this idea holds out, we might eventually do away with the Turing test for artificial intelligence -which was always so anthropocentric as to be, well, just a little bit silly ;)

The idea is that the frontal neocortex -not the older (and possibly more complex) pre-mammalian brain- is basically a mechanism to predict the future. That the neocortex can be simply modeled as vast networks of hierarchical elements that predict their future input sequences.
So, as far as i can make out, predictive subsystems
- that are based on a hierarchical theory of memory,
- and are strongly sequential/temporal.

And the model of the neocortex plugs into other components of the brain (that aren't modeled here). The intelligence (the memory and predictive components) providing the input to the older, pre-mammalian brain, which then uses this intelligent prediction to drive action and behavior via those older systems.

Anyway, sounds good so far. Probably worth keeping an eye out for On Intelligence, his book on the subject

refactoring the mind

Listen to A monk's guide to changing your mind (mp3 audio)
I like that he places the practice of meditation within solid neurological and cognitive frameworks.. mostly because i'm tired of all the new-agey crap that gets unintentionally bundled in with one sitting quietly for a few minutes everyday and breathing.

check these bookmarks for some material in text form.


UPDATE: The above link the the audio file is broken - but I've found a very similar talk by the same monk, hosted here: http://diydharma.org/audio/download/3593/206%20-%20The%20science%20of%20meditation.mp3

notquitemindreading

listen :BBC - Radio 4 - Frontiers 06/06/2007.

beware - cognitive hazards..

A Cognitive bias is distortion in the way humans perceive reality. Check out a really useful list of cognitive biases here. Some of these have been verified empirically in the field of psychology, others are considered general categories of bias.

also posted as 26 reasons what you think is right, is wrong

wired to connect

Science & the City | Webzine of the New York Academy of Sciences: "Wired to Connect - Daniel Goleman
In Social Intelligence, psychologist and science writer Daniel Goleman, known for his 1995 bestseller Emotional Intelligence, introduces new concepts in neuroscience that reveal how human brains are designed to connect."

listen to the interview directly here, or download the mp3 from here. hes got some good ideas in there.
Science And The City has an good store of articles and podcasts - most of those i've listened to so far have been worth the effort.

happiness is ... er ....

well, listen to what some scientists have to say on the subject. The audio below is taken from a recent podcast on the science of happiness, from the canadian science radio show Quirks and Quarks. pretty useful.

Listen to or download the mp3 audio file or Ogg audio file . (what's ogg?)

(i'm off to try and stimulate my left prefrontal cortex ;-)

BBC Radio 4 - Reith Lectures 2003 - The Emerging Mind

BBC - Radio 4 - Reith Lectures 2003 - The Emerging Mind: "Vilayanur S. Ramachandran" - Brilliant audio lectures from the forefront of evolutionary neuropsychology

Lecture 4 covering synesthesia and the evolution of language was particularly funky. you just need realplayer (downloadable from the bbc site) to listen.