Neural net architecture for rate-varying inputs

Details Neural net architecture for rate-varying inputs Neural net architecture for rate-varying inputs

1990-09-20

1993-06-15

Fleming, Michael R.

Electrical audio signal processing systems and devices

Hearing aids, electrical

Specified casing or housing

381 45, 395 22, G10L 504, G10L 500

Patent

active

052206408

ABSTRACT:
A neural net architecture provides for the recognition of an input signal which is a rate variant of a learned signal pattern, reducing the neural net training requirements. The duration of a digital sampling of the input signal is scaled by a time-scaling network, creating a multiplicity of scaled signals which are then compared to memorized signal patterns contained in a self-organizing feature map. The feature map outputs values which indicate how well the scaled input signals match various learned signal patterns. A comparator determines which one of the values is greatest, thus indicating a best match between the input signal and one of the learned signal patterns.

REFERENCES:
patent: 4406001 (1983-09-01), Klasco et al.
patent: 4852170 (1989-07-01), Bordeaux
patent: 4885791 (1989-12-01), Fujii et al.
patent: 4933973 (1990-06-01), Porter
patent: 4982433 (1991-01-01), Yajima et al.
patent: 5053974 (1991-10-01), Penz
Glover, D. E., "An Optical Fourier/Electronic Neurocomputer Automated Inspection System" Proc. IEEE Intl. Conf. on Neural Networks, 1988, 569-576.
Kohonen, T., "The Neural Phonetic Typwriter", Computer, Mar. 1988, pp. 11-22.
Hammerstrom, D., "A VLSI Architecture for High-Performance, Low Cost, On-Chip Learning", Feb. 1990.
Park et al., "A Novel Structure for Real-Time Digital Sample-Rate Converters with Finite Precision Error Analysis" 1991, pp. 3613-3616.
Hecht-Nielsel, "Neurocomputing: picking the human brain", IEEE Spectrum, Mar. 1988, pp. 36-41.
Gevarter, W. B., Artificial Intelligence Expert Systems Computer Vision and Natural Language Processing, Noyer Publications, 1984, 127-133.
Rabiner et al., Digital Processing of Speech Signals, Prentice-Hall, 1978, 26-31.

Affiliated with

Also associated with

Rating

Neural net architecture for rate-varying inputs does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural net architecture for rate-varying inputs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural net architecture for rate-varying inputs will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1049098