A fully flexible circuit implementation of clique-based neural networks in 65-nm CMOS - Archive ouverte HAL
Communication Dans Un Congrès Année : 2018

A fully flexible circuit implementation of clique-based neural networks in 65-nm CMOS

Résumé

Clique-based neural networks implement low- complexity functions working with a reduced connectivity be- tween neurons. Thus, they address very specific applications operating with a very low energy budget. This paper proposes a flexible and iterative neural architecture able to implement multiple types of clique-based neural networks of up to 3968 neurons. The circuit has been integrated in a ST 65-nm CMOS ASIC and validated in the context of ECG classification. The network core reacts in 83ns to a stimulation and occupies a 0.21mm 2 silicon area.
Fichier non déposé

Dates et versions

hal-01849349 , version 1 (26-07-2018)

Identifiants

Citer

Benoit Larras, Paul Chollet, Cyril Lahuec, Fabrice Seguin, Matthieu Arzel. A fully flexible circuit implementation of clique-based neural networks in 65-nm CMOS. ISCAS 2018 : IEEE International Symposium on Circuits and Systems (ISCAS), May 2018, Firenze, Italy. ⟨10.1109/ISCAS.2018.8350954⟩. ⟨hal-01849349⟩
178 Consultations
0 Téléchargements

Altmetric

Partager

More