VLSI Complexity Reduction by Piece-Wise Approximation of the Sigmoid Function

Valeriu Beiu; Jan A. Peperstraete; Joos Vandewalle; Rudy Lauwereins

VLSI Complexity Reduction by Piece-Wise Approximation of the Sigmoid Function

Valeriu Beiu, Jan A. Peperstraete, Joos Vandewalle, Rudy Lauwereins

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

Abstract

The paper is devoted to show that there are simple and accurate ways to compute a sigmoid nonlinearity in digital h ardware by piece-wise linearization. This is done as the computations involved are complex, but even more interesting, for the data compression performed by the sigmoid, which can half the number of Boolean functions to be further implemented. We detail such an approximation algorithm, and analyze its ac curacy, showing im- provements over the previous known algorithms. The algorithm uses only ad - ditions/subtractions and shifts (multiplications by powers of 2), supporting our claim of "simplicity".

Original language	English
Title of host publication	European Symposium on Artificial Neural Networks
Publication status	Published - Apr 20 1994
Event	ESANN'94 - Brussels, Belgium Duration: Apr 20 1994 → …

Conference

Conference	ESANN'94
Period	4/20/94 → …

Access to Document

http://www.researchgate.net/publication/221165140_VLSI_complexity_reduction_by_piece-wise_approximation_of_the_sigmoid_function

Cite this

@inproceedings{aaceb7f6175e45a29dbdd9cf9ffc902b,

title = "VLSI Complexity Reduction by Piece-Wise Approximation of the Sigmoid Function",

abstract = "The paper is devoted to show that there are simple and accurate ways to compute a sigmoid nonlinearity in digital h ardware by piece-wise linearization. This is done as the computations involved are complex, but even more interesting, for the data compression performed by the sigmoid, which can half the number of Boolean functions to be further implemented. We detail such an approximation algorithm, and analyze its ac curacy, showing im- provements over the previous known algorithms. The algorithm uses only ad - ditions/subtractions and shifts (multiplications by powers of 2), supporting our claim of {"}simplicity{"}.",

author = "Valeriu Beiu and Peperstraete, {Jan A.} and Joos Vandewalle and Rudy Lauwereins",

year = "1994",

month = apr,

day = "20",

language = "English",

booktitle = "European Symposium on Artificial Neural Networks",

note = "ESANN'94 ; Conference date: 20-04-1994",

}

TY - GEN

T1 - VLSI Complexity Reduction by Piece-Wise Approximation of the Sigmoid Function

AU - Beiu, Valeriu

AU - Peperstraete, Jan A.

AU - Vandewalle, Joos

AU - Lauwereins, Rudy

PY - 1994/4/20

Y1 - 1994/4/20

N2 - The paper is devoted to show that there are simple and accurate ways to compute a sigmoid nonlinearity in digital h ardware by piece-wise linearization. This is done as the computations involved are complex, but even more interesting, for the data compression performed by the sigmoid, which can half the number of Boolean functions to be further implemented. We detail such an approximation algorithm, and analyze its ac curacy, showing im- provements over the previous known algorithms. The algorithm uses only ad - ditions/subtractions and shifts (multiplications by powers of 2), supporting our claim of "simplicity".

AB - The paper is devoted to show that there are simple and accurate ways to compute a sigmoid nonlinearity in digital h ardware by piece-wise linearization. This is done as the computations involved are complex, but even more interesting, for the data compression performed by the sigmoid, which can half the number of Boolean functions to be further implemented. We detail such an approximation algorithm, and analyze its ac curacy, showing im- provements over the previous known algorithms. The algorithm uses only ad - ditions/subtractions and shifts (multiplications by powers of 2), supporting our claim of "simplicity".

M3 - Conference contribution

BT - European Symposium on Artificial Neural Networks

T2 - ESANN'94

Y2 - 20 April 1994

ER -

VLSI Complexity Reduction by Piece-Wise Approximation of the Sigmoid Function

Abstract

Conference

Access to Document

Fingerprint

Cite this