Asymmetrically extremely dilute neural networks with non-trivial dynamics

Details Asymmetrically extremely dilute neural networks with non-trivial dynamics Asymmetrically extremely dilute neural networks with non-trivial dynamics

2004-04-30

arxiv.org/abs/cond-mat/0404742v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

15 pages, postscript figures

Scientific paper

We study graded response attractor neural networks with asymmetrically extremely dilute interactions and Langevin dynamics. We solve our model in the thermodynamic limit using generating functional analysis, and find (in contrast to the binary neurons case) that even in statics one cannot eliminate the non-persistent order parameters. The macroscopic dynamics is driven by the (non-trivial) joint distribution of neurons and fields, rather than just the (Gaussian) field distribution. We calculate phase transition lines and present simulation results in support of our theory.

Affiliated with

Also associated with

No associations

Rating

Asymmetrically extremely dilute neural networks with non-trivial dynamics 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 Asymmetrically extremely dilute neural networks with non-trivial dynamics, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Asymmetrically extremely dilute neural networks with non-trivial dynamics will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-286768