DocumentCode :
1518650
Title :
Visual Pattern Extraction Using Energy-Efficient “2-PCM Synapse” Neuromorphic Architecture
Author :
Bichler, Olivier ; Suri, Manan ; Querlioz, Damien ; Vuillaume, Dominique ; DeSalvo, Barbara ; Gamrat, Christian
Author_Institution :
Embedded Comput. Lab., CEA-LIST, Gif-sur-Yvette, France
Volume :
59
Issue :
8
fYear :
2012
Firstpage :
2206
Lastpage :
2214
Abstract :
We introduce a novel energy-efficient methodology “2-PCM Synapse” to use phase-change memory (PCM) as synapses in large-scale neuromorphic systems. Our spiking neural network architecture exploits the gradual crystallization behavior of PCM devices for emulating both synaptic potentiation and synaptic depression. Unlike earlier attempts to implement a biological-like spike-timing-dependent plasticity learning rule with PCM, we use a simplified rule where long-term potentiation and long-term depression can both be produced with a single invariant crystallizing pulse. Our architecture is simulated on a special purpose event-based simulator, using a behavioral model for the PCM devices validated with electrical characterization. The system, comprising about 2 million synapses, directly learns from event-based dynamic vision sensors. When tested with real-life data, it is able to extract complex and overlapping temporally correlated features such as car trajectories on a freeway. Complete trajectories can be learned with a detection rate above 90 %. The synaptic programming power consumption of the system during learning is estimated and could be as low as 100 nW for scaled down PCM technology. Robustness to device variability is also evidenced.
Keywords :
neural chips; neural net architecture; phase change memories; 2-PCM synapse neuromorphic architecture; PCM device; PCM technology; biological-like spike-timing-dependent plasticity learning rule; car trajectory; device variability; energy-efficient methodology; event-based dynamic vision sensor; event-based simulator; freeway; gradual crystallization behavior; neuromorphic system; phase change memory; single invariant crystallizing pulse; spiking neural network architecture; synaptic depression; synaptic potentiation; synaptic programming power consumption; visual pattern extraction; Computer architecture; Crystallization; Neuromorphics; Neurons; Phase change materials; Timing; 2-PCM synapse; Neuromorphic system; phase-change materials; spike-timing-dependent plasticity; spiking neural network;
fLanguage :
English
Journal_Title :
Electron Devices, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9383
Type :
jour
DOI :
10.1109/TED.2012.2197951
Filename :
6202332
Link To Document :
بازگشت