Suppression of chaos in a partially driven recurrent neural network

Abstract

The dynamics of recurrent neural networks (RNNs), and particularly their response to inputs, play a critical role in information processing. In many applications of RNNs, only a specific subset of the neurons generally receive inputs. However, it remains to be theoretically clarified how the restriction of the input to a specific subset of neurons affects the network dynamics. Considering RNNs with such restricted input, we investigate how the proportion, $p$, of the neurons receiving inputs (the "inputs neurons") and the strength of the input signals affect the dynamics by analytically deriving the conditional maximum Lyapunov exponent. Our results show that for sufficiently large $p$, the maximum Lyapunov exponent decreases monotonically as a function of the input strength, indicating the suppression of chaos, but if $p$ is smaller than a critical threshold, $p_c$, even significantly amplified inputs cannot suppress spontaneous chaotic dynamics. Furthermore, although the value of $p_c$ is seemingly dependent on several model parameters, such as the sparseness and strength of recurrent connections, it is proved to be intrinsically determined solely by the strength of chaos in spontaneous activity of the RNN. This is to say, despite changes in these model parameters, it is possible to represent the value of $p_c$ as a common invariant function by appropriately scaling these parameters to yield the same strength of spontaneous chaos. Our study suggests that if $p$ is above $p_c$, we can bring the neural network to the edge of chaos, thereby maximizing its information processing capacity, by amplifying inputs.

arXiv comment7 pages, 4 figures

References in corpus (9)

• Complexity without chaos: Plasticity within random recurrent networks generates robust timing and motor control
• Recurrent Network Models Of Sequence Generation And Memory
• Stimulus-Dependent Suppression of Chaos in Recurrent Neural Networks
• Distributions of covariances as a window into the operational regime of neuronal networks
• Two types of criticality in the brain
• Optimal sequence memory in driven random networks
• Edge of chaos and avalanches in neural networks with heavy-tailed synaptic weight distribution
• Mean Field Theory of Dynamical Systems Driven by External Signals
• Optimal short-term memory before the edge of chaos in driven random recurrent networks

Cited by in corpus (5)

• Oscillations enhance time-series prediction in reservoir computing with feedback
• Neuronal correlations shape the scaling behavior of memory capacity and nonlinear computational capability of reservoir recurrent neural networks
• Irreversibility in Non-reciprocal Chaotic Systems
• Universal Scaling Laws of Absorbing Phase Transitions in Artificial Deep Neural Networks
• Hierarchy of chaotic dynamics in random modular networks