Title |
Plasticity in memristive devices for spiking neural networks
|
---|---|
Published in |
Frontiers in Neuroscience, March 2015
|
DOI | 10.3389/fnins.2015.00051 |
Pubmed ID | |
Authors |
Sylvain Saïghi, Christian G. Mayr, Teresa Serrano-Gotarredona, Heidemarie Schmidt, Gwendal Lecerf, Jean Tomas, Julie Grollier, Sören Boyn, Adrien F. Vincent, Damien Querlioz, Selina La Barbera, Fabien Alibart, Dominique Vuillaume, Olivier Bichler, Christian Gamrat, Bernabé Linares-Barranco |
Abstract |
Memristive devices present a new device technology allowing for the realization of compact non-volatile memories. Some of them are already in the process of industrialization. Additionally, they exhibit complex multilevel and plastic behaviors, which make them good candidates for the implementation of artificial synapses in neuromorphic engineering. However, memristive effects rely on diverse physical mechanisms, and their plastic behaviors differ strongly from one technology to another. Here, we present measurements performed on different memristive devices and the opportunities that they provide. We show that they can be used to implement different learning rules whose properties emerge directly from device physics: real time or accelerated operation, deterministic or stochastic behavior, long term or short term plasticity. We then discuss how such devices might be integrated into a complete architecture. These results highlight that there is no unique way to exploit memristive devices in neuromorphic systems. Understanding and embracing device physics is the key for their optimal use. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Switzerland | 2 | 33% |
Japan | 1 | 17% |
Unknown | 3 | 50% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 6 | 100% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 5 | 2% |
United Kingdom | 1 | <1% |
Switzerland | 1 | <1% |
Russia | 1 | <1% |
Belgium | 1 | <1% |
Unknown | 262 | 97% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 58 | 21% |
Researcher | 45 | 17% |
Student > Master | 31 | 11% |
Student > Bachelor | 23 | 8% |
Student > Doctoral Student | 14 | 5% |
Other | 38 | 14% |
Unknown | 62 | 23% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 77 | 28% |
Physics and Astronomy | 41 | 15% |
Materials Science | 33 | 12% |
Computer Science | 14 | 5% |
Chemistry | 11 | 4% |
Other | 24 | 9% |
Unknown | 71 | 26% |