Multitasking associative networks

Details Multitasking associative networks Multitasking associative networks

2011-11-22

arxiv.org/abs/1111.5191v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

7 pages, 5 figures

Scientific paper

We introduce a bipartite, diluted and frustrated, network as a sparse restricted Boltzman machine and we show its thermodynamical equivalence to an associative working memory able to retrieve multiple patterns in parallel without falling into spurious states typical of classical neural networks. We focus on systems processing in parallel a finite (up to logarithmic growth in the volume) amount of patterns, mirroring the low-level storage of standard Amit-Gutfreund-Sompolinsky theory. Results obtained trough statistical mechanics, signal-to-noise technique and Monte Carlo simulations are overall in perfect agreement and carry interesting biological insights. Indeed, these associative networks pave new perspectives in the understanding of multitasking features expressed by complex systems, e.g. neural and immune networks.

Affiliated with

Also associated with

No associations

Rating

Multitasking associative networks 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 Multitasking associative networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multitasking associative networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-553278