Efficient Hopfield pattern recognition on a scale-free neural network

Details Efficient Hopfield pattern recognition on a scale-free neural network Efficient Hopfield pattern recognition on a scale-free neural network

2002-12-26

arxiv.org/abs/cond-mat/0212601v2

Physics

Condensed Matter

Statistical Mechanics

8 pages including 4 figures

Scientific paper

10.1140/epjb/e2003-00114-7

Neural networks are supposed to recognise blurred images (or patterns) of $N$ pixels (bits) each. Application of the network to an initial blurred version of one of $P$ pre-assigned patterns should converge to the correct pattern. In the "standard" Hopfield model, the $N$ "neurons'' are connected to each other via $N^2$ bonds which contain the information on the stored patterns. Thus computer time and memory in general grow with $N^2$. The Hebb rule assigns synaptic coupling strengths proportional to the overlap of the stored patterns at the two coupled neurons. Here we simulate the Hopfield model on the Barabasi-Albert scale-free network, in which each newly added neuron is connected to only $m$ other neurons, and at the end the number of neurons with $q$ neighbours decays as $1/q^3$. Although the quality of retrieval decreases for small $m$, we find good associative memory for $1 \ll m \ll N$. Hence, these networks gain a factor $N/m \gg 1$ in the computer memory and time.

Affiliated with

Also associated with

No associations

Rating

Efficient Hopfield pattern recognition on a scale-free neural network 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 Efficient Hopfield pattern recognition on a scale-free neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Efficient Hopfield pattern recognition on a scale-free neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-604958