Skip to main content

Home/ Artificial Intelligence Research/ Group items tagged HTM

Rss Feed Group items tagged

Matvey Ezhov

PLoS Biology: Towards a Mathematical Theory of Cortical Micro-circuits (about Hawkins' ... - 1 views

  • The theoretical setting of hierarchical Bayesian inference is gaining acceptance as a framework for understanding cortical computation.
    • Matvey Ezhov
       
      Statement needs checking
  • Friston recently expanded on this to suggest an inversion method for hierarchical Bayesian dynamic models and to point out that the brain, in principle, has the infrastructure needed to invert hierarchical dynamic models [6].
  • In a recent review, Hegde and Felleman pointed out that the “Bayesian framework is not yet a neural model. [The Bayesian] framework currently helps explain the computations that underlie various brain functions, but not how the brain implements these computations” [2]. This paper is an attempt to fill this gap by deriving a computational model for cortical circuits based on the mathematics of Bayesian belief propagation in the context of a particular Bayesian framework called Hierarchical Temporal Memory (HTM).
  • ...3 more annotations...
  • This paper's other author, George, recognized that the Memory-Prediction framework could be formulated in Bayesian terms and given a proper mathematical foundation [8],[9].
  • Several researchers have proposed detailed models for cortical circuits [10]–[12].
  • Other researchers [4],[13] have proposed detailed mechanisms by which Bayesian belief propagation techniques can be implemented in neurons.
    • Matvey Ezhov
       
      Николаю Сибирцеву: ты искал именно это
Matvey Ezhov

Biological Basis of HTMs - Numenta.com - 3 views

  •  
    исключительно интересно. Проштудирую
Matvey Ezhov

Ben Goertzel - Patterns of Awareness - 0 views

  •  
    A Pattern-Theoretic, Panpsychist Solution to the Hard Problem of Consciousness
Matvey Ezhov

On Biological and Digital Intelligence - 0 views

  • In essence, Hawkins argues that, to whatever extent the concept of “consciousness” can’t be boiled down to brain theory, it’s simply a bunch of hooey.
    • Matvey Ezhov
       
      Not true!
  • in which conscious experience is more foundational than physical systems or linguistic communications
  • Conscious experiences are associated with patterns, and patterns are associated with physical systems, but none of these is fully reducible to the other. 
  • ...22 more annotations...
  • He makes the correct point that roughly-human-level AI’s will have dramatically different strengths and weaknesses from human being, due to different sensors and actuators and different physical infrastructures for their cognitive dynamics.  But he doesn’t even touch the notion of self-modifying AI – the concept that once an AI gets smart enough to modify its own code, it’s likely to get exponentially smarter and smarter until it’s left us humans in the dust.
    • Matvey Ezhov
       
      Совершенно не имеет отношения к теме, подход Хокинса легко масштабируется до сверх- и сверх-сверх-сверхчеловеческого интеллекта.
  • therefore if AI closely enough emulates the human brain it won’t radically self-modify either
  • Rather, I think the problem is that the field of AI has come to focus on “narrow AI” – programs that solve particularly, narrowly-defined problems – rather than “artificial general intelligence” (AGI). 
  • cognitive science, artificial general intelligence, philosophy of mind and abstract mathematics
    • Matvey Ezhov
       
      т.о. Гортзел признается, что вообще принимает и не считает нужным принимать нейронауку в расчет, т.е. опирается только на эмпирические представления о том, как работает сознание.
  • So what we’re doing is creating commercial narrow AI programs, using the software framework that we’re building out with our AGI design in mind.
    • Matvey Ezhov
       
      и в этом его большое отличие от платформы Хокинса, которая имеет одинаковую структуру для всех ее применений
  • I tend to largely agree with his take on the brain
  • I think he oversimplifies some things fairly seriously – giving them very brief mention when they’re actually quite long and complicated stories.  And some of these omissions, in my view, are not mere “biological details” but are rather points of serious importance for his program of abstracting principles from brain science and then re-concretizing these principles in the context of digital software.
  • One point Hawkins doesn’t really cover is how a mind/brain chooses which predictions to make, from among the many possible predictions that exist.
    • Matvey Ezhov
       
      тут он вроде бы прав...
  • Hawkins proposes that there are neurons or neuronal groups that represent patterns as “tokens,” and that these tokens are then incorporated along with other neurons or neuronal groups into larger groupings representing more abstract patterns.  This seems clearly to be correct, but he doesn’t give much information on how these tokens are supposed to be formed. 
  • So, what’s wrong with Hawkins’ picture of brain function?  Nothing’s exactly wrong with it, so far as I can tell.
  • But Edelman then takes the concept one step further and talks about “neural maps” – assemblies of neuronal groups that carry out particular perception, cognition or action functions.  Neural maps, in essence, are sets of neuronal groups that host attractors of neurodynamics.  And Edelman then observes, astutely, that the dynamics of the population of neuronal groups, over time, is likely to obey a form of evolution by natural selection.
  • How fascinating if the brain also operates in this way!
    • Matvey Ezhov
       
      да нифига... слов нет
  • Hawkins argues that creativity is essentially just metaphorical thinking, generalization based on memory.  While this is true in a grand sense, it’s not a very penetrating statement.
  • Evolutionary learning is the most powerful general search mechanism known to computer science, and is also hypothesized by Edelman to underly neural intelligence.  This sort of idea, it seems to me, should be part of any synthetic approach to brain function.
  • Hawkins mentions the notion, and observes correctly that Hebbian learning in the brain is a lot subtler than the simple version that Donald Hebb laid out in the late 40’s.   But he largely portrays these variations as biological details, and then shifts focus to the hierarchical architecture of the cortex. 
  • Hawkins’ critique of AI, which in my view is overly harsh.  He dismisses work on formal logic based reasoning as irrelevant to “real intelligence.” 
  • So – to sum up – I think Hawkins’ statements about brain function are pretty much correct
  • What he omits are, for instance,   The way the brain displays evolutionary learning as a consequence of the dynamics of multiple attractors involving sets of neural clusters The way the brain may emergently give rise to probabilistic reasoning via the statistical coordination of Hebbian learning
  • Learning of predictive patterns requires an explicit or implicit search through a large space of predictive patterns; evolutionary learning provides one approach to this problem, with computer science foundations and plausible connections to brain function; again, Hawkins does not propose any concrete alternative.
  • crucial question of how far one has to abstract away from brain function, to get to something that can be re-specialized into efficient computer software.  My intuition is that this will require a higher level of abstraction than Hawkins seems to believe.  But I stress that this is a matter of intuitive judgment – neither of us really knows.
  • Of course, to interpret the Novamente design as an “abstraction from the brain” is to interpret this phrase in a fairly extreme sense – we’re abstracting general processes like probabilistic inference and evolutionary learning and general properties like hierarchical structure from the brain, rather than particular algorithms. 
    • Matvey Ezhov
       
      наконец-то он сказал это
  • Although I’m (unsurprisingly) most psyched about the Novamente approach, I think it’s also quite worthwhile to pursue AGI approaches that are closer to the brain level – there’s a large space between detailed brain simulation and Novamente, including neuron-level simulations, neural-cluster-level simulations, and so forth. 
thinkahol *

All In The Mind - 10 October 2009 - You are not a self! Bodies, brains and the nature o... - 0 views

  •  
    German philosopher of mind Thomas Metzinger is one of the world's top researchers on consciousness, instrumental in its renaissance as a respectable problem for scientific enquiry. From out-of-body experiences to lucid dreaming, anarchic hand syndrome to phantom limbs, his investigations have taken him to places few dare to go. Be spooked, bewildered and amazed.
Matvey Ezhov

Perceptual Learning Relies On Local Motion Signals To Learn Global Motion - 0 views

  • The brain first perceives changes in visual input (local motion) in the primary visual cortex. The local motion signals are then integrated in the later visual processing stages and interpreted as global motion in the higher-level processes. But when subjects in a recent experiment using moving dots were asked to detect global motion (the overall direction of the dots moving together), the results show that their learning relied on more local motion processes (the movement of dots in small areas) than global motion areas.
  • show that the improvement in detection of global motion is not due to learning of the global motion but to learning of local motion of the moving dots in the test.
Matvey Ezhov

Genetics Of Patterning The Cerebral Cortex: How Stem Cells Yield Functional Regions In ... - 0 views

  • Their discovery reveals a critical period during which a LIM homeodomain transcription factor known as Lhx2 decides over the progenitors' regional destiny: Once the window of opportunity closes, their fate is sealed.
Matvey Ezhov

New Light On Nature Of Broca's Area: Rare Procedure Documents How Human Brain Computes ... - 0 views

  • Our task involved both reading and speaking, and we found that aspects of word identity, grammar and pronunciation are all computed within Broca's area.
Matvey Ezhov

Time-keeping Brain Neurons Discovered - 3 views

  • An MIT team led by Institute Professor Ann Graybiel has found groups of neurons in the primate brain that code time with extreme precision.
  • The neurons are located in the prefrontal cortex and the striatum, both of which play important roles in learning, movement and thought control.
  • The research team trained two macaque monkeys to perform a simple eye-movement task. After receiving the "go" signal, the monkeys were free to perform the task at their own speed. The researchers found neurons that consistently fired at specific times -- 100 milliseconds, 110 milliseconds, 150 milliseconds and so on -- after the "go" signal.
  •  
    Its would be difficult, if neurons of that kind have not be discovered. Obliviously, we have millions of it in our brains. For make time-keeping neurons we need (in simplest case) only 2 neurons with reciprocal connections. More units in circle - more time to delay - more time to "keep". Also, not single "time keeping neurons" but time keeping circles. Such clear understating of processes on neuronal level is completely impossible without Brainbug play experience. Think about it!
Matvey Ezhov

Nanowire Biocompatibility In The Brain: So Far So Good - 0 views

  • One advantage of nanoscale electrodes is that they can register and stimulate the tiniest components of the brain.
  •  
    Researchers at Lund University in Sweden have managed for the first time to carry out successful experiments involving the injection of so-called 'nanowires.'
Matvey Ezhov

Can We 'Learn To See?': Study Shows Perception Of Invisible Stimuli Improves With Training - 0 views

  • A Harvard Medical School study last year found that one blindsight patient could maneuver down a hallway filled with obstacles, even though the subject could not actually see. Schwiedrzik said the new research may help blindsight patients gain conscious awareness of what their minds can see, and he suggested that new research should address whether the brains in blindsight patients and people with normal vision process the information the same way.
Matvey Ezhov

Karl Friston - 0 views

  • as providing the most promising attempt at a unified theory of brain functions
  • Through a Darwinian process, selecting from the competing models the one best supported by the evidence, a basis for action is chosen.
1 - 20 of 20
Showing 20 items per page