Transient dynamics for sequence processing neural networks

Abstract

An exact solution of the transient dynamics for a sequential associative memory model is discussed through both the path-integral method and the statistical neurodynamics. Although the path-integral method has the ability to give an exact solution of the transient dynamics, only stationary properties have been discussed for the sequential associative memory. We have succeeded in deriving an exact macroscopic description of the transient dynamics by analyzing the correlation of crosstalk noise. Surprisingly, the order parameter equations of this exact solution are completely equivalent to those of the statistical neurodynamics, which is an approximation theory that assumes crosstalk noise to obey the Gaussian distribution. In order to examine our theoretical findings, we numerically obtain cumulants of the crosstalk noise. We verify that the third- and fourth-order cumulants are equal to zero, and that the crosstalk noise is normally distributed even in the non-retrieval case. We show that the results obtained by our theory agree with those obtained by computer simulations. We have also found that the macroscopic unstable state completely coincides with the separatrix.

21 pages, 4 figures

Cited by in corpus (14)

• The path-integral analysis of an associative memory model storing an infinite number of finite limit cycles
• Hopfield Neuronal Network of Fractional Order: A note on its numerical integration
• The signal-to-noise analysis of the Little-Hopfield model revisited
• Mean-field dynamics of sequence processing neural networks with finite connectivity
• Generating functional analysis of CDMA detection dynamics
• Topology and Dynamics of Attractor Neural Networks: The Role of Loopiness
• Low-dimensional chaos induced by frustration in a non-monotonic system
• Bifurcation analysis in an associative memory model
• Stochastic transitions of attractors in associative memory models with correlated noise
• Period-two cycles in a feed-forward layered neural network model with symmetric sequence processing
• Theory of Recurrent Neural Network with Common Synaptic Inputs
• Pattern reconstruction and sequence processing in feed-forward layered neural networks near saturation
• Parallel dynamics of continuous Hopfield model revisited
• Symmetric sequence processing in a recurrent neural network model with a synchronous dynamics