Abstract
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 examined. The analysis of the parameter space reveals the following main finding: a perceptron with a monotonic function can produce fragile chaos only, whereas a non-monotonic function can generate robust chaos as well. For non-monotonic functions, the dimension of the attractor can be controlled monotonically by tuning a natural parameter in the model.