Physics – Condensed Matter
Scientific paper
1994-02-22
Physics
Condensed Matter
13 pages (with figures), LaTex (RevTex), to appear on Phys.Rev.E (RC)
Scientific paper
10.1103/PhysRevE.49.R1823
In the context of attractor neural networks, we study how the equilibrium analog neural activities, reached by the network dynamics during memory retrieval, may improve storage performance by reducing the interferences between the recalled pattern and the other stored ones. We determine a simple dynamics that stabilizes network states which are highly correlated with the retrieved pattern, for a number of stored memories that does not exceed $\alpha_{\star} N$, where $\alpha_{\star}\in[0,0.41]$ depends on the global activity level in the network and $N$ is the number of neurons.
Brunel Nicolas
Zecchina Riccardo
No associations
LandOfFree
Response Functions Improving Performance in Analog Attractor Neural 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 Response Functions Improving Performance in Analog Attractor Neural Networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Response Functions Improving Performance in Analog Attractor Neural Networks will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-124084