141 citations · 293 across the 9 of their papers we have counts for
4 papers · 1 filter
Learning and generation of long-range correlated sequences
A. Priel, I. Kanter
We study the capability to learn and to generate long-range, power-law correlated sequences by a fully connected asymmetric network. The focus is set on the ability of neural netwo…
Robust chaos generation by a perceptron
A. Priel, I. Kanter
The properties of time series generated by a perceptron with monotonic and non-monotonic transfer function, where the next input vector is determined from past output values, are e…
Long-term properties of time series generated by a perceptron with various transfer functions
A. Priel, I. Kanter
We study the effect of various transfer functions on the properties of a time series generated by a continuous-valued feed-forward network in which the next input vector is determi…
Noisy time series generation by feed-forward networks
A Priel, I Kanter, D A Kessler
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…