TY - GEN
T1 - All-implicants neural networks for efficient Boolean function representation
AU - Buffoni, Federico
AU - Gianini, Gabriele
AU - Damiani, Ernesto
AU - Granitzer, Michael
N1 - Funding Information:
Acknowledgements. The authors acknowledge the support of the Information and Communication TechnologyFund (ICT Fund) at EBTIC/Khalifa University, Abu Dhabi, UAE.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/7
Y1 - 2018/9/7
N2 - Boolean classifiers can be evolved by means of genetic algorithms. This can be done within an intercommunicating island system, of evolutionary niches, undergoing cycles that alternate long periods of isolation to short periods of information exchange. In these settings, the efficiency of the communication is a key requirement. In the present work, we address this requirement by providing a technique for efficiently representing and transmitting differential encodings of Boolean functions. We introduce a new class of Boolean Neural Networks (BNN), the all-implicants BNN, and show that this representation supports efficient update communication, better than the classical representation, based on truth tables.
AB - Boolean classifiers can be evolved by means of genetic algorithms. This can be done within an intercommunicating island system, of evolutionary niches, undergoing cycles that alternate long periods of isolation to short periods of information exchange. In these settings, the efficiency of the communication is a key requirement. In the present work, we address this requirement by providing a technique for efficiently representing and transmitting differential encodings of Boolean functions. We introduce a new class of Boolean Neural Networks (BNN), the all-implicants BNN, and show that this representation supports efficient update communication, better than the classical representation, based on truth tables.
UR - http://www.scopus.com/inward/record.url?scp=85057769438&partnerID=8YFLogxK
U2 - 10.1109/ICCC.2018.00019
DO - 10.1109/ICCC.2018.00019
M3 - Conference contribution
AN - SCOPUS:85057769438
T3 - Proceedings - 2018 IEEE International Conference on Cognitive Computing, ICCC 2018 - Part of the 2018 IEEE World Congress on Services
SP - 82
EP - 86
BT - Proceedings - 2018 IEEE International Conference on Cognitive Computing, ICCC 2018 - Part of the 2018 IEEE World Congress on Services
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Cognitive Computing, ICCC 2018
Y2 - 2 July 2018 through 7 July 2018
ER -