Analog Synapse Device With 5-b MLC and Improved Data Retention for Neuromorphic System
| Autor: | Myonglae Chu, Hyunsang Hwang, Jaesung Park, Euijun Cha, Byung-Geun Lee, Sang Ho Oh, Kyungjoon Baek, Sang-Gyun Gi, Kibong Moon |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
010302 applied physics
Materials science Artificial neural network Interface (computing) 02 engineering and technology 021001 nanoscience & nanotechnology 01 natural sciences Electronic Optical and Magnetic Materials Synapse Neuromorphic engineering 0103 physical sciences Electrode Scalability Electronic engineering Electrical and Electronic Engineering Data retention 0210 nano-technology Energy (signal processing) |
| Zdroj: | IEEE Electron Device Letters. 37:1067-1070 |
| ISSN: | 1558-0563 0741-3106 |
| DOI: | 10.1109/led.2016.2583545 |
| Popis: | This letter presents an investigation of analog synapse characteristics of a PCMO-based interface switching device with varying electrode materials. In comparison with the filamentary switching device having only 1-b storage and variability issues, the interface switching devices exhibit excellent electrical properties, such as 5-b (32-level) multi-level cell characteristics, wafer-scale switching uniformity, and scalability of the switching energy with device area. To improve data retention of the interface switching device, we propose a Mo electrode to increase the oxidation barrier height ( $\sim 0.4$ eV) that, in turn, significantly improves the retention time and pattern classification accuracy of neural networks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|