Low Power, CMOS-MoS2 Memtransistor based Neuromorphic Hybrid Architecture for Wake-Up Systems
| Autor: | Pratik Kumar, Chetan Singh Thakur, Arindam Ghosh, André van Schaik, Tathagata Paul, Sarthak Gupta |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
lcsh:Medicine
02 engineering and technology Two-dimensional materials 010402 general chemistry 01 natural sciences Article Bottleneck Electronic Systems Engineering (Formerly Centre for Electronic Design & Technology) Electronic devices lcsh:Science Block (data storage) Multidisciplinary Physics lcsh:R Energy consumption 021001 nanoscience & nanotechnology Electrical and electronic engineering 0104 chemical sciences Power (physics) Architecture framework CMOS Computer architecture Neuromorphic engineering lcsh:Q 0210 nano-technology Realization (systems) |
| Zdroj: | Scientific Reports Scientific Reports, Vol 9, Iss 1, Pp 1-9 (2019) |
| ISSN: | 2045-2322 |
| DOI: | 10.1038/s41598-019-51606-x |
| Popis: | Neuromorphic architectures have become essential building blocks for next-generation computational systems, where intelligence is embedded directly onto low power, small area, and computationally efficient hardware devices. In such devices, realization of neural algorithms requires storage of weights in digital memories, which is a bottleneck in terms of power and area. We hereby propose a biologically inspired low power, hybrid architectural framework for wake-up systems. This architecture utilizes our novel high-performance, ultra-low power molybdenum disulphide (MoS2) based two-dimensional synaptic memtransistor as an analogue memory. Furthermore, it exploits random device mismatches to implement the population coding scheme. Power consumption per CMOS neuron block was found to be 3 nw in the 65 nm process technology, while the energy consumption per cycle was 0.3 pJ for potentiation and 20 pJ for depression cycles of the synaptic device. The proposed framework was demonstrated for classification and regression tasks, using both off-chip and simplified on-chip sign-based learning techniques. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|