A recurrent neural network controller and learning algorithm for the on-line learning control of autonomous underwater vehicles

On-line identification and reconstruction of finite automata with generalized recurrent neural networks

In this paper finite automata are treated as general discrete dynamical systems from the viewpoint of systems theory. The unconditional on-line identification of an unknown finite automaton is the problem considered. A generalized architecture of recurrent neural networks with a corresponding on-line learning scheme is proposed as a solution to the problem. An on-line rule-extraction algorithm is further introduced. The architecture presented, the on-line learning scheme and the on-line rule-extraction method are tested on different, strongly connected automata, ranging from a very simple example with two states only to a more interesting and complex one with 64 states; the results of both training and extraction processes are very promising.

Two Timescale Analysis of the Alopex Algorithm for Optimization

Alopex is a correlation-based gradient-free optimization technique useful in many learning problems. However, there are no analytical results on the asymptotic behavior of this algorithm. This article presents a new version of Alopex that can be analyzed using techniques of two timescale stochastic approximation method. It is shown that the algorithm asymptotically behaves like a gradient-descent method, though it does not need (or estimate) any gradient information. It is also shown, through simulations, that the algorithm is quite effective.