arXiv · cond-mat/0510169
Theory of Recurrent Neural Network with Common Synaptic Inputs
Abstract
We discuss the effects of common synaptic inputs in a recurrent neural network. Because of the effects of these common synaptic inputs, the correlation between neural inputs cannot be ignored, and thus the network exhibits sample dependence. Networks of this type do not have well-defined thermodynamic limits, and self-averaging breaks down. We therefore need to develop a suitable theory without relying on these common properties. While the effects of the common synaptic inputs have been analyzed in layered neural networks, it was apparently difficult to analyze these effects in recurrent neural networks due to feedback connections. We investigated a sequential associative memory model as an example of recurrent networks and succeeded in deriving a macroscopic dynamical description as a recurrence relation form of a probability density function.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Masaki Kawamura, Michiko Yamana, Masato Okada. 2005-10-07. Theory of Recurrent Neural Network with Common Synaptic Inputs. https://doi.org/10.1143/jpsj.74.2961. https://searcharxiv.com/abs/cond-mat/0510169
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.