Comparing distributed and local neural classifiers for the recognition of Japanese phonemes
Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Japonya, 25 - 29 Ekim 1993, cilt.1, ss.239-242, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 1
- Basıldığı Şehir: Nagoya
- Basıldığı Ülke: Japonya
- Sayfa Sayıları: ss.239-242
- Boğaziçi Üniversitesi Adresli: Evet
Özet
The comparative performances of distributed and local neural networks for the speech recognition problem is investigated. Distributed networks' hidden units use the sigmoid non-linearity which have global response. We have used the back-propagation rule with three error measures: mean square error, cross entropy, and combinational performance. The hidden units of local networks respond only to inputs in a certain local region in the input space. We used k-nearest neighbor (knn), Gaussian-based knn, learning vector quantization, and grow and learn methods. Phoneme recognition experiments are conducted using the /b,d,g,m,n,N/ set of the Japanese vocabulary for the speaker dependent case. Three criteria are taken for comparison: correct classification of the test set, network size, and learning time.