Learning by message-passing in networks of discrete synapses

Details Learning by message-passing in networks of discrete synapses Learning by message-passing in networks of discrete synapses

2005-11-07

arxiv.org/abs/cond-mat/0511159v2

Phys. Rev. Lett. 96, 030201 (2006)

Physics

Condensed Matter

Disordered Systems and Neural Networks

4 pages, 3 figures; references updated and minor corrections; accepted in PRL

Scientific paper

10.1103/PhysRevLett.96.030201

We show that a message-passing process allows to store in binary "material" synapses a number of random patterns which almost saturates the information theoretic bounds. We apply the learning algorithm to networks characterized by a wide range of different connection topologies and of size comparable with that of biological systems (e.g. $n\simeq10^{5}-10^{6}$). The algorithm can be turned into an on-line --fault tolerant-- learning protocol of potential interest in modeling aspects of synaptic plasticity and in building neuromorphic devices.

Affiliated with

Also associated with

No associations

Rating

Learning by message-passing in networks of discrete synapses does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning by message-passing in networks of discrete synapses, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning by message-passing in networks of discrete synapses will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-336881