Speaker
Description
Neuromorphic systems are circuit interconnects designed to emulate the neural processing of a biological brain. Artificial synapses can be reproduced by controlling emergent complex phenomena observed in a distinctive class of self-assembly (network) materials exhibiting memristive behaviour in their contact points. Such memristive interfaces work as smart resistive switches whose resistance depends on the history of the input voltage/current. When integrated into the right circuit environment, these networks can mimic certain brain functions, e.g., data recognition, time-series learning, memorization, and fault-tolerant processing. To date, the design of neuromorphic network devices is restricted to highly customized approaches, with no standardization of their training and fabrication protocols. We developed an innovative computational platform designed to model the memristive characteristics and dynamical response of neuromorphic network devices with adaptive behaviour towards changes in their electrical properties. In particular, we demonstrate that network materials made of randomly distributed core-shell nanowires are promising memristive architectures for neuromorphic applications and reservoir-based computing operations such as electrical potentiation and waveform transformation, due to their connectivity, recurrence, and neurosynaptic-like behaviours. Our findings are expected to have important implications for the development of neuromorphic devices based on reservoir computing and complex nanomaterials.
| Keyword-1 | Neuromorphic systems |
|---|---|
| Keyword-2 | Nanomaterials |
| Keyword-3 | Memristive systems |