Training auto-associative recurrent neural network with preprocessed training data
Document Type
Conference Proceeding
Publication Date
8-19-1993
Abstract
The Auto-Associative Recurrent Network (AARN), a modified version of the Simple Recurrent Network (SRN) can be trained to behave as recognizer of a language generated by a regular grammar. The network is trained successfully on an unbounded number of sequences of the language, generated randomly from the Finite State Automaton (FSA) of the language. But the training algorithm fails when training is restricted to a fixed finite set of examples. Here, we present a new algorithm for training the AARN from a finite set of language examples. A tree is constructed by preprocessing the training data. The AARN is trained with sequences generated randomly from the tree. The results of the simulations experiments are discussed.
Identifier
84993748320 (Scopus)
Publication Title
Proceedings of SPIE the International Society for Optical Engineering
External Full Text Location
https://doi.org/10.1117/12.152645
e-ISSN
1996756X
ISSN
0277786X
First Page
420
Last Page
428
Volume
1966
Recommended Citation
Maskara, Aran and Noetzel, Andrew, "Training auto-associative recurrent neural network with preprocessed training data" (1993). Faculty Publications. 16998.
https://digitalcommons.njit.edu/fac_pubs/16998
