Constrained chaos in three-module neural network enables to execute multiple tasks simultaneously.

Constrained chaos introduced into a three-module neural network having feedforward inter-module structure could have potential abilities to execute multiple tasks simultaneously. Each module consists of a large number of binary state (±1) neurons. The entire activity pattern (neuron state) is updated by recurrent rule under certain external input to the first module and input to post-module from pre-module.

Simultaneous multichannel signal transfers via chaos in a recurrent neural network.

We propose neural network model that demonstrates the phenomenon of signal transfer between separated neuron groups via other chaotic neurons that show no apparent correlations with the input signal. The model is a recurrent neural network in which it is supposed that synchronous behavior between small groups of input and output neurons has been learned as fragments of high-dimensional memory patterns, and depletion of neural connections results in chaotic wandering dynamics. Computer experiments show that when a strong oscillatory signal is applied to an input group in the chaotic regime, the signal is successfully transferred to the corresponding output group, although no correlation is observed between the input signal and the intermediary neurons.