On the computational power of Elman-style recurrent networks
- 1 July 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 6 (4) , 1000-1004
- https://doi.org/10.1109/72.392262
Abstract
Recently, Elman (1991) has proposed a simple recurrent network which is able to identify and classify temporal patterns. Despite the fact that Elman networks have been used extensively in many different fields, their theoretical capabilities have not been completely defined. Research in the 1960's showed that for every finite state machine there exists a recurrent artificial neural network which approximates it to an arbitrary degree of precision. This paper extends that result to architectures meeting the constraints of Elman networks, thus proving that their computational power is as great as that of finite state machines.Keywords
This publication has 7 references indexed in Scilit:
- From lattices of phonemes to sentences: a recurrent neural network approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Distributed representations, simple recurrent networks, and grammatical structureMachine Learning, 1991
- Phonetic to acoustic mapping using recurrent neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Finding structure in timeCognitive Science, 1990
- A connectionist approach to the recognition of trends in time-ordered medical parametersComputer Methods and Programs in Biomedicine, 1990
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943