Valeriu Beiu, John G. Taylor  Home/Search
Context Related
| lanl.gov/nisprojects/dap...NN9_7_96.PS Cached: PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
PS.gz PS Image Update HelpFrom: lanl.gov/nisproje...bibliography (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper aims to examine the circuit complexity of sigmoid activation feedforward artificial neural networks by placing them amongst several classic Boolean and threshold gate circuit complexity classes. The starting point is the class NN k defined by Shawe-Taylor et al. (1992). For a better characterisation, we introduce two additional classes NN D k and NN D, e k having less restrictive conditions than NN k concerning fan-in and accuracy, and proceed to prove relations amongst these ... (Update)
Similar documents based on text: More All
0.4: Optimal VLSI Implementation Of Neural Networks - VLSI-friendly.. - Beiu (1996) (Correct)
0.4: Area-Time Performances of Some Neural Computations - Beiu, Peperstraete.. (1994) (Correct)
0.3: A VLSI-Optimal Constructive Algorithm For Classification.. - Draghici, BEIU, al. (Correct)
Related documents from co-citation: More All
2: Threshold logic (context) - Hampel, Winder - 1971
2: VLSI Complexity of Discrete Neural Networks (context) - Beiu - 1998
2: Threshold Logic (context) - Hu - 1965
BibTeX entry: (Update)
V. Beiu & J.G. Taylor. On the Circuit Complexity of Sigmoid Feedforward Neural Networks. Neural Networks, 9(7), 1155-1171, 1996. http://citeseer.ist.psu.edu/beiu96circuit.html More
@article{ beiu96circuit,
author = "V. Beiu and J. G. Taylor",
title = "On the Circuit Complexity of Sigmoid Feedforward Neural Networks",
journal = "Neural Networks",
volume = "9",
number = "7",
pages = "1155--1171",
year = "1996",
url = "citeseer.ist.psu.edu/beiu96circuit.html" }
Citations (may not include all citations):201 Parallel Prefix Computations (context) - Ladner, Fischer - 1980
189 Algebraic Methods in the Theory of Lower Bounds for Boolean .. (context) - Smolensky - 1987
92 Constant Depth Reducibility (context) - Chandra, Stockmeyer et al. - 1984
83 The Monotone Circuit Complexity of Boolean Functions (context) - Alon, Boppana - 1987
82 Monotone Circuits for Connectivity Require Super--Logarithmi.. (context) - Karchmer, Wigderson - 1988
76 A Regular Layout for Parallel Adders - Brent, Kung - 1982
59 Harmonic Analysis of Polynomial Threshold Functions (context) - Bruck - 1990
44 Monotone Circuits for Matching Require Linear Depth - Raz, Wigderson - 1990
31 the Power of Threshold Circuits with Small Weights (context) - Siu, Bruck - 1991
31 the Power of Threshold Circuits with Small Weights (context) - Siu, Bruck - 1992
29 Circuit Complexity and Neural Networks (context) - Parberry - 1994
27 Neural Computation of Arithmetic Functions (context) - Siu, Bruck - 1990
18 Depth--Size Tradeoffs for Neural Computations (context) - Siu, Roychowdhury et al. - 1991
14 Application of Matrix Methods to the Theory of Lower Bounds .. (context) - Razborov - 1990
12 On Small Depth Threshold Circuits - Razborov
11 Area--Time Optimal Adder Design (context) - Wei, Thompson - 1990
10 Some Notes on Threshold Circuits and Multiplication in Depth.. (context) - Hofmeister, Hohberg et al. - 1991
10 the Power of Networks of Majority Functions - Mayoraz - 1991
10 Optimal Lower Bounds on the Depth of Polynomial Size Thresho.. (context) - Wegener - 1993
9 Efficient Decomposition of COMPARISON and Its Applications - Beiu, Peperstraete et al.
8 Rational Approximation Techniques for Analysis of Neural Net.. (context) - Siu, Roychowdhury et al. - 1994
8 On Connectionist Models (context) - Hong - 1987
8 VLSI Complexity of Discrete Neural Networks (context) - Beiu - 1996
8 Implementing the Algebra of Logic Functions in Terms of Boun.. (context) - Lupanov - 1961
7 Threshold Logic (context) - Lewis, Coates - 1967
6 Entropy and the Complexity of Feedforward Neural Networks (context) - Williamson - 1991
6 Classes of Feedforward Neural Nets and Their Circuit Complex.. (context) - Shawe-Taylor, Anthony et al. - 1992
5 The Synthesis of Networks from Threshold Elements (context) - Nechiporuk - 1964
5 A Comparison Study of Binary Feedforward Neural Networks and.. (context) - Andree, Barkema et al. - 1993
5 Lower Bounds on Threshold and Related Circuits via Communica.. - Roychowdhury, Orlitsky et al. - 1994
5 Threshold Logic (context) - Hu - 1965
4 Explicit Construction of Depth--2 Majority Circuits for Comp.. (context) - Alon, Bruck - 1991
4 Computing with Almost Optimal Size Threshold Circuits (context) - Siu, Roychowdhury et al. - 1990
4 Area--Time Performances of Some Neural Computations - Beiu, Peperstraete et al.
3 On Bounded---Depth Threshold Circuits for Pattern Functions (context) - Albrecht - 1992
3 the Complexity of Neural Networks with Sigmoid Units (context) - Siu - 1992
3 Complexity in Neural Systems (context) - Abu-Mostafa - 1989
3 COMPARISON and Threshold Gate Decomposition (context) - Beiu, Peperstraete et al.
3 Training a Limited -Interconnect (context) - Walker, Haghighi et al. - 1989
2 Optimal Parallel ADDITION Means Constant Fan--In Threshold G.. (context) - Beiu, Peperstraete et al.
2 Taylor Circuit Complexity of Sigmoid NNs: 39 Manuscript (context) - Beiu - 1992
2 Taylor Circuit Complexity of Sigmoid NNs: 40 Manuscript (context) - Beiu - 1992
2 the Circuit Complexity of Feedforward Neural Networks - Beiu, Peperstraete et al.
1 Modelling the Complexity of Parallel and VLSI Computations w.. (context) - Papadopoulos, Andronikos - 1995
Documents on the same site (http://nis-www.lanl.gov/nis-projects/daps/new/bib/bibliography.html): More
A VLSI-Optimal Constructive Algorithm For Classification.. - Draghici, BEIU, al. (Correct)
Optimal VLSI Implementation Of Neural Networks - VLSI-friendly.. - Beiu (1996) (Correct)
E1.4 Digital integrated circuit implementations - Valeriu Be Iu (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC