Abbreviations
Download:
|
|
by J. A. P Erez-ortiz, J. Calera-rubio, M. L. Forcada
http://www.dlsi.ua.es/~japerez/pub/ps/icann2001a-postera0.ps.gz
Add To MetaCart
Abstract:
This paper studies the use of recurrent neural networks for predicting the next symbol in a sequence. The focus is on online prediction, a task much harder than the classical offline grammatical inference with neural networks. Different kinds of sequence sources are considered: finitestate machines, chaotic sources, and texts in human language. Two algorithms are used for network training: real-time recurrent learning and the decoupled extended Kalman filter.
Citations
| 1179 | Finding structure in time – Elman - 1990 |
| 142 | Finite state automata and simple recurrent networks – Cleeremans, Servan-Schreiber, et al. - 1989 |
| 45 | Decoupled Extended Kalman Filter Training of Feedforward Layered Networks – Puskorius, Feldkamp - 1991 |
| 18 | Sequential Neural Text Compression – Schmidhuber, Heil - 1996 |
| 10 | A learning algorithm for continually training recurrent neural networks – Williams, Zipser - 1989 |
| 6 | Arithmetic coding + statistical modeling = data compression – Nelson - 1991 |
| 1 | K oteles (1999), "Extracting finite-state representations from recurrent neural networks trained on chaotic symbolic sequences – no, P |
