CONCENTRATION INFORMATION IN TIME: ANALOG NEURAL NETWORKS WITH APPLICATIONS TO SPEECH RECOGNITION PROBLEMS.

D. W. Tank; J. J. Hopfield

CONCENTRATION INFORMATION IN TIME: ANALOG NEURAL NETWORKS WITH APPLICATIONS TO SPEECH RECOGNITION PROBLEMS.

D. W. Tank, J. J. Hopfield

Research output: Contribution to conference › Paper › peer-review

Abstract

An electronic implementation of a neural network for a real-time speech recognition problem is described. The circuit is completely analog with the outputs of the circuit driven by the speech input. The computation is totally asynchronous; there is no system clock. The time-dependent synaptic connections and the resulting dynamics of the circuit can be considered as an organizer of information over several time scales.

Original language	English (US)
Pages	iv/455-468
State	Published - 1987
Externally published	Yes

All Science Journal Classification (ASJC) codes

General Engineering

Cite this

@conference{e76982e776344ed8a32840162feb9e86,

title = "CONCENTRATION INFORMATION IN TIME: ANALOG NEURAL NETWORKS WITH APPLICATIONS TO SPEECH RECOGNITION PROBLEMS.",

abstract = "An electronic implementation of a neural network for a real-time speech recognition problem is described. The circuit is completely analog with the outputs of the circuit driven by the speech input. The computation is totally asynchronous; there is no system clock. The time-dependent synaptic connections and the resulting dynamics of the circuit can be considered as an organizer of information over several time scales.",

author = "Tank, \{D. W.\} and Hopfield, \{J. J.\}",

year = "1987",

language = "English (US)",

pages = "iv/455--468",

}

TY - CONF

T1 - CONCENTRATION INFORMATION IN TIME

T2 - ANALOG NEURAL NETWORKS WITH APPLICATIONS TO SPEECH RECOGNITION PROBLEMS.

AU - Tank, D. W.

AU - Hopfield, J. J.

PY - 1987

Y1 - 1987

N2 - An electronic implementation of a neural network for a real-time speech recognition problem is described. The circuit is completely analog with the outputs of the circuit driven by the speech input. The computation is totally asynchronous; there is no system clock. The time-dependent synaptic connections and the resulting dynamics of the circuit can be considered as an organizer of information over several time scales.

AB - An electronic implementation of a neural network for a real-time speech recognition problem is described. The circuit is completely analog with the outputs of the circuit driven by the speech input. The computation is totally asynchronous; there is no system clock. The time-dependent synaptic connections and the resulting dynamics of the circuit can be considered as an organizer of information over several time scales.

UR - https://www.scopus.com/pages/publications/0001510011

UR - https://www.scopus.com/inward/citedby.url?scp=0001510011&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0001510011

SP - iv/455-468

ER -

CONCENTRATION INFORMATION IN TIME: ANALOG NEURAL NETWORKS WITH APPLICATIONS TO SPEECH RECOGNITION PROBLEMS.

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this