The time dimension of neural network models
- 1 July 1994
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGART Bulletin
- Vol. 5 (3) , 36-44
- https://doi.org/10.1145/181911.181917
Abstract
This review attempts to provide an insightful perspective on the role of time within neural network models and the use of neural networks for problems involving time. The most commonly used neural network models are defined and explained giving mention to important technical issues but avoiding great detail. The relationship between recurrent and feedforward networks is emphasised, along with the distinctions in their practical and theoretical abilities. Some practical examples are discussed to illustrate the major issues concerning the application of neural networks to data with various types of temporal structure, and finally some highlights of current research on the more difficult types of problems are presented.Keywords
This publication has 17 references indexed in Scilit:
- IPA: improved phone modelling with recurrent neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Application of neural networks for system identification of an adsorption columnNeural Computing & Applications, 1993
- The principles and practice of time series forecasting and business modelling using neural netsNeural Computing & Applications, 1993
- Learning and Extracting Finite State Automata with Second-Order Recurrent Neural NetworksNeural Computation, 1992
- A Fixed Size Storage O(n3) Time Complexity Learning Algorithm for Fully Recurrent Continually Running NetworksNeural Computation, 1992
- A study of network dynamicsJournal of Statistical Physics, 1990
- A time-delay neural network architecture for isolated word recognitionNeural Networks, 1990
- A Learning Algorithm for Continually Running Fully Recurrent Neural NetworksNeural Computation, 1989
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989