Noisy time series generation by feed-forward networks

Abstract

We study the properties of a noisy time series generated by a continuous-valued feed-forward network in which the next input vector is determined from past output values. Numerical simulations of a perceptron-type network exhibit the expected broadening of the noise-free attractor, without changing the attractor dimension. We show that the broadening of the attractor due to the noise scales inversely with the size of the system ,$N$, as $1/\sqrt{N}$. We show both analytically and numerically that the diffusion constant for the phase along the attractor scales inversely with $N$. Hence, phase coherence holds up to a time that scales linearly with the size of the system. We find that the mean first passage time, $t$, to switch between attractors depends on $N$, and the reduced distance from bifurcation $\tau$ as $t=a\frac{N}{\tau }\exp (b\tau N^{1/2})$, where $b$ is a constant which depends on the amplitude of the external noise. This result is obtained analytically for small $\tau$ and confirmed by numerical simulations.

13 Latex pages including 16 figures

Cited by in corpus (4)

• Long-term properties of time series generated by a perceptron with various transfer functions
• Generation of unpredictable time series by a Neural Network
• Neural Networks, Game Theory and Time Series Generation
• Mean First Passage Time in Periodic Attractors