Confined PCM-based Analog Synaptic Devices offering Low Resistance-drift and 1000 Programmable States for Deep Learning
| Autor: | K. Suu, G. Fraczak, Wanki Kim, Stefano Ambrogio, M. Longstreet, Jin-Ping Han, T. Masuda, Fabio Carta, Praneet Adusumilli, John Bruley, Nanbo Gong, Matthew J. BrightSky, Robert L. Bruce, Hsinyu Tsai |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
010302 applied physics
Materials science business.industry Deep learning Linearity 02 engineering and technology 021001 nanoscience & nanotechnology 01 natural sciences Noise (electronics) Phase-change memory 0103 physical sciences Optoelectronics Artificial intelligence 0210 nano-technology business Low resistance MNIST database |
| Zdroj: | 2019 Symposium on VLSI Technology. |
| Popis: | We have demonstrated, for the first time, a combination of outstanding linearity of analog programming with matched PCM pairs, small analog programming noise, an extremely low resistance drift (R-drift) coefficient (0.005, median) and high endurance for a CVD-based confined phase change memory (PCM) with a thin metallic liner. In-depth analysis of linear analog programming is also presented. MNIST simulations using a pair of these confined PCM devices as a synaptic element yield a high test accuracy of 95%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|