SARDNET: A Self-Organizing Feature mAP for Sequences
Abstract
A self-organizing neural network for sequence classification called SARDNET is described and analyzed experimentally. SARDNET extends the Kohonen Feature Map architecture with activation re(cid:173) tention and decay in order to create unique distributed response patterns for different sequences. SARDNET yields extremely dense yet descriptive representations of sequential input in very few train(cid:173) ing iterations. The network has proven successful on mapping ar(cid:173) bitrary sequences of binary and real numbers, as well as phonemic representations of English words. Potential applications include isolated spoken word recognition and cognitive science models of sequence processing.
Cite
Text
James and Miikkulainen. "SARDNET: A Self-Organizing Feature mAP for Sequences." Neural Information Processing Systems, 1994.Markdown
[James and Miikkulainen. "SARDNET: A Self-Organizing Feature mAP for Sequences." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/james1994neurips-sardnet/)BibTeX
@inproceedings{james1994neurips-sardnet,
title = {{SARDNET: A Self-Organizing Feature mAP for Sequences}},
author = {James, Daniel L. and Miikkulainen, Risto},
booktitle = {Neural Information Processing Systems},
year = {1994},
pages = {577-584},
url = {https://mlanthology.org/neurips/1994/james1994neurips-sardnet/}
}