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 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.
All-Implicants Neural Networks for Efficient Boolean Function Representation / F. Buffoni, G. Gianini, E. Damiani, M. Granitzer - In: 2018 IEEE International Conference on Cognitive Computing (ICCC)[s.l] : IEEE, 2018. - ISBN 9781538672419. - pp. 82-86 (( convegno ICCC tenutosi a San Francisco nel 2018 [10.1109/ICCC.2018.00019].
All-Implicants Neural Networks for Efficient Boolean Function Representation
G. Gianini
Secondo
;E. DamianiPenultimo
;
2018
Abstract
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 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.File | Dimensione | Formato | |
---|---|---|---|
PUBLISHED_VERSION_ICCC2018.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
191.25 kB
Formato
Adobe PDF
|
191.25 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.