Efficient simulation of finite automata by neural nets
Journal of the ACM (JACM)
Learning finite machines with self-clustering recurrent networks
Neural Computation
Computation: finite and infinite machines
Computation: finite and infinite machines
High-order neural network structures for identification of dynamical systems
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
This paper presents a new architecture of neural networks for representing deterministic finite state automata. The proposed model is a class of high-order recurrent neural networks. It is capable of representing FSA with the network size being smaller than the existing models proposed so far. We also propose an identification method of FSA from a given set of input and output data by training the proposed model of neural networks.