Universality of reservoir systems with recurrent neural networks

arXiv:2403.01900v1 Announce Type: cross
Abstract: Approximation capability of reservoir systems whose reservoir is a recurrent neural network (RNN) is discussed. In our problem setting, a reservoir system approximates a set of functions just by adjusting its linear readout while the reservoir is fixed. We will show what we call uniform strong universality of a family of RNN reservoir systems for a certain class of functions to be approximated. This means that, for any positive number, we can construct a sufficiently …

abstract adjusting approximation arxiv call capability cs.lg cs.ne functions linear network networks neural network neural networks recurrent neural network recurrent neural networks rnn set show systems type uniform will