A Single Neuron Can Recognize Patterns

Neocortical neurons have thousands of excitatory synapses. It is a mystery how neurons integrate the input from so many synapses and what kind of large-scale network behavior this enables. It has been previously proposed that non-linear properties of dendrites enable neurons to recognize multiple patterns. In this paper we extend this idea by showing that a neuron with several thousand synapses arranged along active dendrites can learn to accurately and robustly recognize hundreds of unique patterns of cellular activity, even in the presence of large amounts of noise and pattern variation. We then propose a neuron model where some of the patterns recognized by a neuron lead to action potentials and define the classic receptive field of the neuron, whereas the majority of the patterns recognized by a neuron act as predictions by slightly depolarizing the neuron without immediately generating an action potential. We then present a network model based on neurons with these properties and show that the network learns a robust model of time-based sequences. Given the similarity of excitatory neurons throughout the neocortex and the importance of sequence memory in inference and behavior, we propose that this form of sequence memory is a universal property of neocortical tissue. We further propose that cellular layers in the neocortex implement variations of the same sequence memory algorithm to achieve different aspects of inference and behavior. The neuron and network models we introduce are robust over a wide range of parameters as long as the network uses a sparse distributed code of cellular activations. The sequence capacity of the network scales linearly with the number of synapses on each neuron. Thus neurons need thousands of synapses to learn the many temporal patterns in sensory stimuli and motor sequences.


Folksonomies: artificial intelligence neurons ai

/health and fitness/disease (0.571268)
/technology and computing/hardware/computer (0.196683)
/technology and computing/software (0.147053)

neuron (0.907347 (positive:0.288792)), Patterns Neocortical neurons (0.865299 (negative:-0.283788)), Single Neuron (0.725639 (negative:-0.283788)), sequence memory (0.666546 (positive:0.256889)), neuron lead (0.639235 (positive:0.586799)), neuron model (0.635596 (positive:0.586799)), neuron act (0.634006 (neutral:0.000000)), excitatory synapses (0.601885 (negative:-0.283788)), robustly recognize hundreds (0.556301 (positive:0.403006)), excitatory neurons (0.522671 (neutral:0.000000)), large-scale network behavior (0.522530 (neutral:0.000000)), neocortex implement variations (0.490678 (neutral:0.000000)), classic receptive field (0.488723 (positive:0.586799)), sequence memory algorithm (0.478264 (neutral:0.000000)), sparse distributed code (0.434195 (neutral:0.000000)), active dendrites (0.331135 (positive:0.403006)), neocortical tissue (0.311695 (positive:0.256889)), sequence capacity (0.290331 (negative:-0.220328)), cellular activity (0.279305 (positive:0.403006)), time-based sequences (0.275492 (positive:0.826515)), multiple patterns (0.271956 (negative:-0.243712)), cellular activations (0.268648 (neutral:0.000000)), large amounts (0.268410 (neutral:0.000000)), unique patterns (0.266563 (positive:0.403006)), non-linear properties (0.266333 (negative:-0.243712)), cellular layers (0.262813 (neutral:0.000000)), action potentials (0.259233 (positive:0.586799)), robust model (0.259023 (positive:0.826515)), sensory stimuli (0.258985 (negative:-0.482424)), pattern variation (0.256112 (neutral:0.000000))

Neuron (0.966977): dbpedia | freebase | opencyc
Action potential (0.961697): dbpedia | freebase
Chemical synapse (0.794200): dbpedia | freebase
Membrane potential (0.709971): dbpedia | freebase
Axon (0.664544): dbpedia | freebase | opencyc
Cellular neuroscience (0.624680): dbpedia | freebase
Synapse (0.535462): dbpedia | freebase
Retina (0.532977): dbpedia | freebase | opencyc

 Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex
Periodicals>Journal Article:  Hawkins, Jeff and Ahmad, Subutai (31 Oct 2015), Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex, Retrieved on 2015-11-19
  • Source Material [arxiv.org]
  • Folksonomies: artificial intelligence neurons ai