Skip to Main content Skip to Navigation
Conference papers

Advanced technologies for brain-inspired computing

F. Clermidy 1 R. Heliot 1 A. Valentian 1 C. Gamrat 2 O. Bichler 2 M. Duranton 2 Bilel Blehadj 3 Olivier Temam 3
1 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
2 DACLE-LIST - Département d'Architectures, Conception et Logiciels Embarqués-LIST
3 Inria Saclay - Ile de France
Abstract : This paper aims at presenting how new technologies can overcome classical implementation issues of Neural Networks. Resistive memories such as Phase Change Memories and Conductive-Bridge RAM can be used for obtaining low-area synapses thanks to programmable resistance also called Memristors. Similarly, the high capacitance of Through Silicon Vias can be used to greatly improve analog neurons and reduce their area. The very same devices can also be used for improving connectivity of Neural Networks as demonstrated by an application. Finally, some perspectives are given on the usage of 3D monolithic integration for better exploiting the third dimension and thus obtaining systems closer to the brain.
Keywords : Advanced technology Monolithic integration Resistive memory Through silicon vias Computer aided design Monolithic integrated circuits Neural networks Analog neurons Random access storage Brain-inspired computing
Document type :
Conference papers
Complete list of metadata
https://hal-cea.archives-ouvertes.fr/cea-01839860
Contributor : Léna Le Roy <>
Submitted on : Monday, July 16, 2018 - 10:06:08 AM
Last modification on : Thursday, June 11, 2020 - 5:04:07 PM

Identifiers

Collections

CEA | DRT | INRIA | LETI | LIST | CEA-GRE

Citation

F. Clermidy, R. Heliot, A. Valentian, C. Gamrat, O. Bichler, et al.. Advanced technologies for brain-inspired computing. 2014 19th Asia and South Pacific Design Automation Conference (ASP-DAC), Jan 2014, Suntec, Singapore. pp.563-569, ⟨10.1109/ASPDAC.2014.6742951⟩. ⟨cea-01839860⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

157