Gamma MLP - using multiple temporal resolutions for improved classification

Steve Lawrence; Andrew D. Back; Ah Chung Tsoi; C. Lee Giles

Gamma MLP - using multiple temporal resolutions for improved classification

Steve Lawrence
, Andrew D. Back
, Ah Chung Tsoi
, C. Lee Giles

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The Gamma multilayer perceptron (MLP) is a MLP with the synaptic weights replaced by gamma filters and associated gain terms throughout all layers and it is applied to speech phoneme recognition problem. The Gamma MLP uses a large range of temporal resolutions for this kind of problem. Further motivation for the Gamma MLP is related to the `curse of dimensionality' and the ability of the Gamma MLP to trade off temporal resolution for memory depth. The memory depth of the network increases without increasing its dimensionality.

Original language	English (US)
Title of host publication	Neural Networks for Signal Processing - Proceedings of the IEEE Workshop
Publisher	IEEE
Pages	256-265
Number of pages	10
State	Published - 1997
Event	Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97 - Amelia Island, FL, USA Duration: Sep 24 1997 → Sep 26 1997

Other

Other	Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97
City	Amelia Island, FL, USA
Period	9/24/97 → 9/26/97

All Science Journal Classification (ASJC) codes

Signal Processing
Software
Electrical and Electronic Engineering

Cite this

@inproceedings{467b29567c2b4c5a8ebab60aed7c8bb8,

title = "Gamma MLP - using multiple temporal resolutions for improved classification",

abstract = "The Gamma multilayer perceptron (MLP) is a MLP with the synaptic weights replaced by gamma filters and associated gain terms throughout all layers and it is applied to speech phoneme recognition problem. The Gamma MLP uses a large range of temporal resolutions for this kind of problem. Further motivation for the Gamma MLP is related to the `curse of dimensionality' and the ability of the Gamma MLP to trade off temporal resolution for memory depth. The memory depth of the network increases without increasing its dimensionality.",

author = "Steve Lawrence and Back, \{Andrew D.\} and Tsoi, \{Ah Chung\} and Giles, \{C. Lee\}",

year = "1997",

language = "English (US)",

pages = "256--265",

booktitle = "Neural Networks for Signal Processing - Proceedings of the IEEE Workshop",

publisher = "IEEE",

note = "Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97 ; Conference date: 24-09-1997 Through 26-09-1997",

}

TY - GEN

T1 - Gamma MLP - using multiple temporal resolutions for improved classification

AU - Lawrence, Steve

AU - Back, Andrew D.

AU - Tsoi, Ah Chung

AU - Giles, C. Lee

PY - 1997

Y1 - 1997

N2 - The Gamma multilayer perceptron (MLP) is a MLP with the synaptic weights replaced by gamma filters and associated gain terms throughout all layers and it is applied to speech phoneme recognition problem. The Gamma MLP uses a large range of temporal resolutions for this kind of problem. Further motivation for the Gamma MLP is related to the `curse of dimensionality' and the ability of the Gamma MLP to trade off temporal resolution for memory depth. The memory depth of the network increases without increasing its dimensionality.

AB - The Gamma multilayer perceptron (MLP) is a MLP with the synaptic weights replaced by gamma filters and associated gain terms throughout all layers and it is applied to speech phoneme recognition problem. The Gamma MLP uses a large range of temporal resolutions for this kind of problem. Further motivation for the Gamma MLP is related to the `curse of dimensionality' and the ability of the Gamma MLP to trade off temporal resolution for memory depth. The memory depth of the network increases without increasing its dimensionality.

UR - https://www.scopus.com/pages/publications/0031351310

UR - https://www.scopus.com/pages/publications/0031351310#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:0031351310

SP - 256

EP - 265

BT - Neural Networks for Signal Processing - Proceedings of the IEEE Workshop

PB - IEEE

T2 - Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97

Y2 - 24 September 1997 through 26 September 1997

ER -

Gamma MLP - using multiple temporal resolutions for improved classification

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this