Abstract
A novel unsupervised neural network for dimensionality reduction that seeks directions emphasizing multimodality is presented, and its connection to exploratory projection pursuit methods is discussed. This leads to a new statistical insight into the synaptic modification equations governing learning in Bienenstock, Cooper, and Munro (BCM) neurons (1982). The importance of a dimensionality reduction principle based solely on distinguishing features is demonstrated using a phoneme recognition experiment. The extracted features are compared with features extracted using a backpropagation network.
References
14
Referenced
68
10.1126/science.3037696
{'key': 'p_5', 'first-page': '3248', 'volume': '2', 'author': 'Bienenstock E. L.', 'year': '1982', 'journal-title': 'I. Neurosci.'}
/ I. Neurosci. by Bienenstock E. L. (1982)10.1073/pnas.85.6.1973
10.1214/aos/1176346703
10.2307/2289161
10.1109/T-C.1974.224051
10.1162/neco.1990.2.3.355
10.1214/aos/1176349519
10.1109/2.36
10.1162/neco.1989.1.1.1
10.1007/BF00275687
10.1007/BF00275079
10.1007/BF00288907
10.1121/1.1908630
Dates
Type | When |
---|---|
Created | 17 years, 5 months ago (March 13, 2008, 12:46 p.m.) |
Deposited | 4 years, 5 months ago (March 12, 2021, 4:31 p.m.) |
Indexed | 4 months, 2 weeks ago (April 17, 2025, 1:50 a.m.) |
Issued | 33 years, 8 months ago (Jan. 1, 1992) |
Published | 33 years, 8 months ago (Jan. 1, 1992) |
Published Print | 33 years, 8 months ago (Jan. 1, 1992) |
@article{Intrator_1992, title={Feature Extraction Using an Unsupervised Neural Network}, volume={4}, ISSN={1530-888X}, url={http://dx.doi.org/10.1162/neco.1992.4.1.98}, DOI={10.1162/neco.1992.4.1.98}, number={1}, journal={Neural Computation}, publisher={MIT Press - Journals}, author={Intrator, Nathan}, year={1992}, month=jan, pages={98–107} }