Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling

In this paper, we present the feed-forward neural network (FFNN) and recurrent neural network (RNN) models for predicting Boolean function complexity (BFC). In order to acquire the training data for the neural networks (NNs), we conducted experiments for a large number of randomly generated single o...

Full description

Bibliographic Details
Main Authors: BEG, A, CHANDANAPRASAD, P
Format: Article
Language:English
Published: PERGAMON-ELSEVIER SCIENCE LTD 2008
Subjects:
Online Access:http://shdl.mmu.edu.my/2670/
http://shdl.mmu.edu.my/2670/1/772.pdf
_version_ 1848790119499169792
author BEG, A
CHANDANAPRASAD, P
BEG, A
author_facet BEG, A
CHANDANAPRASAD, P
BEG, A
author_sort BEG, A
building MMU Institutional Repository
collection Online Access
description In this paper, we present the feed-forward neural network (FFNN) and recurrent neural network (RNN) models for predicting Boolean function complexity (BFC). In order to acquire the training data for the neural networks (NNs), we conducted experiments for a large number of randomly generated single output Boolean functions (BFs) and derived the simulated graphs for number of min-terms against the BFC for different number of variables. For NN model (NNM) development, we looked at three data transformation techniques for pre-processing the NN-training and validation data. The trained NNMs are used for complexity estimation for the Boolean logic expressions with a given number of variables and sum of products (SOP) terms. Both FFNNs and RNNs were evaluated against the ISCAS benchmark results. Our FFNNs and RNNs were able to predict the BFC with correlations of 0.811 and 0.629 with the benchmark results, respectively. (c) 2007 Elsevier Ltd. All rights reserved.
first_indexed 2025-11-14T18:07:33Z
format Article
id mmu-2670
institution Multimedia University
institution_category Local University
language English
last_indexed 2025-11-14T18:07:33Z
publishDate 2008
publisher PERGAMON-ELSEVIER SCIENCE LTD
recordtype eprints
repository_type Digital Repository
spelling mmu-26702014-02-13T03:01:24Z http://shdl.mmu.edu.my/2670/ Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling BEG, A CHANDANAPRASAD, P BEG, A T Technology (General) QA75.5-76.95 Electronic computers. Computer science In this paper, we present the feed-forward neural network (FFNN) and recurrent neural network (RNN) models for predicting Boolean function complexity (BFC). In order to acquire the training data for the neural networks (NNs), we conducted experiments for a large number of randomly generated single output Boolean functions (BFs) and derived the simulated graphs for number of min-terms against the BFC for different number of variables. For NN model (NNM) development, we looked at three data transformation techniques for pre-processing the NN-training and validation data. The trained NNMs are used for complexity estimation for the Boolean logic expressions with a given number of variables and sum of products (SOP) terms. Both FFNNs and RNNs were evaluated against the ISCAS benchmark results. Our FFNNs and RNNs were able to predict the BFC with correlations of 0.811 and 0.629 with the benchmark results, respectively. (c) 2007 Elsevier Ltd. All rights reserved. PERGAMON-ELSEVIER SCIENCE LTD 2008-05 Article NonPeerReviewed text en http://shdl.mmu.edu.my/2670/1/772.pdf BEG, A and CHANDANAPRASAD, P and BEG, A (2008) Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling. Expert Systems with Applications, 34 (4). pp. 2436-2443. ISSN 09574174 http://dx.doi.org/10.1016/j.eswa.2007.04.010 doi:10.1016/j.eswa.2007.04.010 doi:10.1016/j.eswa.2007.04.010
spellingShingle T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
BEG, A
CHANDANAPRASAD, P
BEG, A
Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling
title Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling
title_full Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling
title_fullStr Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling
title_full_unstemmed Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling
title_short Applicability of feed-forward and recurrent neural networks to Boolean function complexity modeling
title_sort applicability of feed-forward and recurrent neural networks to boolean function complexity modeling
topic T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2670/
http://shdl.mmu.edu.my/2670/
http://shdl.mmu.edu.my/2670/
http://shdl.mmu.edu.my/2670/1/772.pdf