Re: Web page about a new neural network theory

m...@xxxxxxxxxxxxxxxxx wrote:
...if there is a
competition element in the learning, as used in the line detection
system then nodes in the output layer become detectors of higher
level features of the input layer...

I had to re-read your site, there you wrote "every time a neuron fires
at the same time as its target, a signal will be sent to nearby
neurons suppressing their learning around that time. This is to
prevent local neurons all learning to respond to the same things. The
thresholds of the neurons in the system should be initialised so that
in general only a small fraction of the nodes in the entire system
should be firing at any one time perhaps <1% perhaps <<1%" - is that a
thing you are referring to?

Meanwhile, do you have a lil bit more formal description, I am
interested to code a little javascript applet to see how your thing
works.

[ comp.ai is moderated ... your article may take a while to appear. ]
.

Relevant Pages

  • Re: Cool visual illusion
    ... >> learners just as evolution must have done? ... > learning and behavioral modifiability. ... other sensory neurons. ...
    (comp.ai.philosophy)
  • Re: Oblvion: Radiant AI in action...
    ... Neuromorphic VLSI for Learning and Memory ... The hippocampus is a brain region responsible for the storage and ... neuromorphic hippocampus consists of 1,280 spiking neurons and 21,504 ... The silicon model learns patterns ...
    (comp.sys.ibm.pc.games.rpg)
  • Re: Web page about a new neural network theory
    ... prevent local neurons all learning to respond to the same things. ... experimenting with different mechanisms for competition and ...
    (comp.ai)
  • Re: General AI vs narrow AI
    ... the brain has multiple types of learning algorithms ... learning by analogy, learning by pattern classification and scene analysis, ... activity in dopaminergic neurons in the basal ...
    (comp.ai.philosophy)