On-Chip Trainable 1.4M 6T2R PCM Synaptic Array with 1.6K Stochastic LIF Neurons for Spiking RBM
| Autor: | Scott C. Lewis, Atsuya Okazaki, Kohji Hosokawa, Junka Okazawa, Megumi Ito, Wanki Kim, Masatoshi Ishii, U. Shin, Wilfried Haensch, Matthew J. BrightSky, Malte J. Rasch, Akiyo Nomura, Sungchul Kim |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0303 health sciences
Restricted Boltzmann machine Contextual image classification Computer science Spice 02 engineering and technology 021001 nanoscience & nanotechnology Phase-change memory 03 medical and health sciences CMOS Crossbar switch 0210 nano-technology Projection (set theory) Algorithm MNIST database 030304 developmental biology |
| Zdroj: | 2019 IEEE International Electron Devices Meeting (IEDM). |
| Popis: | A fully silicon-integrated restricted Boltzmann machine (RBM) with event-driven contrastive divergence (eCD) algorithm is implemented using novel stochastic leaky integrate-and-fire (LIF) neuron circuits and 6-transistor/2- PCM-resistor (6T2R) unit cells on 90-nm CMOS technology. A bidirectional asynchronous spiking signaling scheme over an analog-weighted phase change memory (PCM) crossbar enables spike-timing-dependent plasticity (STDP) as a local weight update rule. This results in concurrent massively- parallel neuronal computation for low-power on-chip training and inference. Experimental image classification using 100 handwritten digit images from the MNIST database demonstrates 92% training accuracy. SPICE simulation abstracted from the fabricated design indicates 8.95 power. A projection to 28-nm technology gives 5.39 pJ per synaptic operation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|