Some novel learning strategies based on set covering in Hamming geometrical space are presented and proved, which are related to the three-layer Boolean neural network (BNN) for implementing an arbitrary Boolean function with low-complexity. Each hidden neuron memorizes a set of learning patterns, then the output layer combines these hidden neurons for explicit output as a Boolean function. The network structure is simple, reliable and can be easily implemented by hardware.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Xiaomin MA, Xian Yang YI, Zhaozhi ZHANG, "Boolean Neural Network Design Using Set Covering in Hamming Geometrical Space" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 10, pp. 2285-2290, October 1999, doi: .
Abstract: Some novel learning strategies based on set covering in Hamming geometrical space are presented and proved, which are related to the three-layer Boolean neural network (BNN) for implementing an arbitrary Boolean function with low-complexity. Each hidden neuron memorizes a set of learning patterns, then the output layer combines these hidden neurons for explicit output as a Boolean function. The network structure is simple, reliable and can be easily implemented by hardware.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_10_2285/_p
Copy
@ARTICLE{e82-a_10_2285,
author={Xiaomin MA, Xian Yang YI, Zhaozhi ZHANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Boolean Neural Network Design Using Set Covering in Hamming Geometrical Space},
year={1999},
volume={E82-A},
number={10},
pages={2285-2290},
abstract={Some novel learning strategies based on set covering in Hamming geometrical space are presented and proved, which are related to the three-layer Boolean neural network (BNN) for implementing an arbitrary Boolean function with low-complexity. Each hidden neuron memorizes a set of learning patterns, then the output layer combines these hidden neurons for explicit output as a Boolean function. The network structure is simple, reliable and can be easily implemented by hardware.},
keywords={},
doi={},
ISSN={},
month={October},}
Copy
TY - JOUR
TI - Boolean Neural Network Design Using Set Covering in Hamming Geometrical Space
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2285
EP - 2290
AU - Xiaomin MA
AU - Xian Yang YI
AU - Zhaozhi ZHANG
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 1999
AB - Some novel learning strategies based on set covering in Hamming geometrical space are presented and proved, which are related to the three-layer Boolean neural network (BNN) for implementing an arbitrary Boolean function with low-complexity. Each hidden neuron memorizes a set of learning patterns, then the output layer combines these hidden neurons for explicit output as a Boolean function. The network structure is simple, reliable and can be easily implemented by hardware.
ER -