Gain elimination from backpropagation neural networks

G. Thimm; E. Fiesler; P. Moerland

Gain elimination from backpropagation neural networks

G. Thimm^*
, E. Fiesler
, P. Moerland

^*Corresponding author for this work

IDIAP Research Institute

Research output: Contribution to conference › Paper › Academic

Abstract

It is shown that the gain of the sigmoidal activation function, used in backpropagation neural networks, can be eliminated since there exists a well-defined relationship between the gain, the learning rate, and the set of initial weights. Similarly, it also possible to eliminate the learning rate by adjusting the gain and the initial weights. The relationship is proven and extended to various variations of the backpropagation learning rule as well as applied to hardware implementations of neural networks.

Original language	English
Pages	365-368
Number of pages	4
Publication status	Published - 1995
Event	Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust Duration: 27 Nov 1995 → 1 Dec 1995

Conference

Conference	Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
City	Perth, Aust
Period	27/11/1995 → 01/12/1995

Cite this

@conference{5bdf2ff48baa42da8b2cd87f44aa7d3d,

title = "Gain elimination from backpropagation neural networks",

abstract = "It is shown that the gain of the sigmoidal activation function, used in backpropagation neural networks, can be eliminated since there exists a well-defined relationship between the gain, the learning rate, and the set of initial weights. Similarly, it also possible to eliminate the learning rate by adjusting the gain and the initial weights. The relationship is proven and extended to various variations of the backpropagation learning rule as well as applied to hardware implementations of neural networks.",

author = "G. Thimm and E. Fiesler and P. Moerland",

year = "1995",

language = "English",

pages = "365--368",

note = "Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) ; Conference date: 27-11-1995 Through 01-12-1995",

}

TY - CONF

T1 - Gain elimination from backpropagation neural networks

AU - Thimm, G.

AU - Fiesler, E.

AU - Moerland, P.

PY - 1995

Y1 - 1995

N2 - It is shown that the gain of the sigmoidal activation function, used in backpropagation neural networks, can be eliminated since there exists a well-defined relationship between the gain, the learning rate, and the set of initial weights. Similarly, it also possible to eliminate the learning rate by adjusting the gain and the initial weights. The relationship is proven and extended to various variations of the backpropagation learning rule as well as applied to hardware implementations of neural networks.

AB - It is shown that the gain of the sigmoidal activation function, used in backpropagation neural networks, can be eliminated since there exists a well-defined relationship between the gain, the learning rate, and the set of initial weights. Similarly, it also possible to eliminate the learning rate by adjusting the gain and the initial weights. The relationship is proven and extended to various variations of the backpropagation learning rule as well as applied to hardware implementations of neural networks.

UR - https://www.scopus.com/pages/publications/0029547759

M3 - Paper

SP - 365

EP - 368

T2 - Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)

Y2 - 27 November 1995 through 1 December 1995

ER -

Gain elimination from backpropagation neural networks

Abstract

Conference

Other files and links

Fingerprint

Cite this