Title |
Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses
|
---|---|
Published in |
Frontiers in Neuroscience, March 2016
|
DOI | 10.3389/fnins.2016.00056 |
Pubmed ID | |
Authors |
Stefano Ambrogio, Nicola Ciocchini, Mario Laudato, Valerio Milo, Agostino Pirovano, Paolo Fantini, Daniele Ielmini |
Abstract |
We present a novel one-transistor/one-resistor (1T1R) synapse for neuromorphic networks, based on phase change memory (PCM) technology. The synapse is capable of spike-timing dependent plasticity (STDP), where gradual potentiation relies on set transition, namely crystallization, in the PCM, while depression is achieved via reset or amorphization of a chalcogenide active volume. STDP characteristics are demonstrated by experiments under variable initial conditions and number of pulses. Finally, we support the applicability of the 1T1R synapse for learning and recognition of visual patterns by simulations of fully connected neuromorphic networks with 2 or 3 layers with high recognition efficiency. The proposed scheme provides a feasible low-power solution for on-line unsupervised machine learning in smart reconfigurable sensors. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 1 | 17% |
Chile | 1 | 17% |
Switzerland | 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 | 3 | 2% |
Unknown | 185 | 98% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 49 | 26% |
Student > Master | 27 | 14% |
Researcher | 26 | 14% |
Student > Doctoral Student | 13 | 7% |
Student > Bachelor | 10 | 5% |
Other | 16 | 9% |
Unknown | 47 | 25% |
Readers by discipline | Count | As % |
---|---|---|
Engineering | 63 | 34% |
Materials Science | 22 | 12% |
Physics and Astronomy | 18 | 10% |
Computer Science | 7 | 4% |
Neuroscience | 5 | 3% |
Other | 15 | 8% |
Unknown | 58 | 31% |