Area-Time Performances of Some Neural Computations

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

Area-Time Performances of Some Neural Computations

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

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

Abstract

The paper aims to show that VLSI efficient implementations of Boolean functions (BFs) using threshold gates (TGs) are possible. First we detail depth-size tradeoffs for COMPARISON when implemented by TGs of variable fan-in (D); a class of polynomially bounded TG circuits having O (lgn ⁄ lgD) depth and O (n ⁄ D) size for any 3 £ D £ clgn, improves on the previous known size O (n). We then proceed to show how fan-in influences the range of weights and of thresholds, and extend these results to Fn,m, the class of functions of n variables having m groups of ones. We conclude that the fan-in could be used by VLSI designers for tuning the area-time performances of neural chips.

Original language	English
Title of host publication	International Symposium on Signal Processing, Robotics and Artificial Neural Networks
Publication status	Published - Apr 25 1994
Event	SPRANN'94 - Lille, France Duration: Apr 25 1994 → …

Conference

Conference	SPRANN'94
Period	4/25/94 → …

Access to Document

http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.29.8874&rep=rep1&type=pdf

Cite this

@inproceedings{3dfcac4b47624b1b95f5e8b38e82ade7,

title = "Area-Time Performances of Some Neural Computations",

abstract = "The paper aims to show that VLSI efficient implementations of Boolean functions (BFs) using threshold gates (TGs) are possible. First we detail depth-size tradeoffs for COMPARISON when implemented by TGs of variable fan-in (D); a class of polynomially bounded TG circuits having O (lgn ⁄ lgD) depth and O (n ⁄ D) size for any 3 £ D £ clgn, improves on the previous known size O (n). We then proceed to show how fan-in influences the range of weights and of thresholds, and extend these results to Fn,m, the class of functions of n variables having m groups of ones. We conclude that the fan-in could be used by VLSI designers for tuning the area-time performances of neural chips.",

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

year = "1994",

month = apr,

day = "25",

language = "English",

booktitle = "International Symposium on Signal Processing, Robotics and Artificial Neural Networks",

note = "SPRANN'94 ; Conference date: 25-04-1994",

}

TY - GEN

T1 - Area-Time Performances of Some Neural Computations

AU - Beiu, Valeriu

AU - Peperstraete, Jan A.

AU - Vandewalle, Joos

AU - Lauwereins, Rudy

PY - 1994/4/25

Y1 - 1994/4/25

N2 - The paper aims to show that VLSI efficient implementations of Boolean functions (BFs) using threshold gates (TGs) are possible. First we detail depth-size tradeoffs for COMPARISON when implemented by TGs of variable fan-in (D); a class of polynomially bounded TG circuits having O (lgn ⁄ lgD) depth and O (n ⁄ D) size for any 3 £ D £ clgn, improves on the previous known size O (n). We then proceed to show how fan-in influences the range of weights and of thresholds, and extend these results to Fn,m, the class of functions of n variables having m groups of ones. We conclude that the fan-in could be used by VLSI designers for tuning the area-time performances of neural chips.

AB - The paper aims to show that VLSI efficient implementations of Boolean functions (BFs) using threshold gates (TGs) are possible. First we detail depth-size tradeoffs for COMPARISON when implemented by TGs of variable fan-in (D); a class of polynomially bounded TG circuits having O (lgn ⁄ lgD) depth and O (n ⁄ D) size for any 3 £ D £ clgn, improves on the previous known size O (n). We then proceed to show how fan-in influences the range of weights and of thresholds, and extend these results to Fn,m, the class of functions of n variables having m groups of ones. We conclude that the fan-in could be used by VLSI designers for tuning the area-time performances of neural chips.

M3 - Conference contribution

BT - International Symposium on Signal Processing, Robotics and Artificial Neural Networks

T2 - SPRANN'94

Y2 - 25 April 1994

ER -

Area-Time Performances of Some Neural Computations

Abstract

Conference

Access to Document

Fingerprint

Cite this