Diffusive Memristor as a Synapse
Neuromorphic computing, systems designed to mimic the biological nervous system, require far less power than current computer processors. The increased efficiency makes feasible artificial intelligence applications for smaller, hand-held devices (e.g. smartphones, tablets). To this end, UMass inventors have designed hardware components that mimic neuronal synapses (Figure A). Specifically, diffusive Ag-in-oxide memristors show a temporal response during and after stimulation similar to that of a biological synapse. The novel diffusive memristor and its synapse-like dynamics enable a direct emulation of both short- and long-term plasticity of biological synapses and represent a major advancement in a hardware implementation for neuromorphic computing. TECHNOLOGY DESCRIPTION ADVANTAGES • High density• Low energy• faithfully emulation of bio-synapses• Intrinsic synaptic dynamics• 3D stackable APPLICATIONS• Memristor for neuromorphic computing• Spiking neural networks (SNNs) • Synapse emulators ABOUT THE INVENTORQiangfei Xia is an associate professor in the department of Electrical and Computer Engineering. Professor Xia’s research is focused on post-CMOS nanodevices, device physics, integrated nanosystems, and enabling nanotechnologies. Jianhua (Joshua) Yang is a professor in the department of Electrical and Computer Engineering. Professor Yang research focuses on unconventional computing technologies, including neuromorphic computing using memristive devices. AVAILABILITY: Available for Licensing and/or Sponsored Research DOCKET: UMA 18-001 PATENT STATUS: Patent Pending NON-CONFIDENTIAL INVENTION DISCLOSURE LEAD INVENTOR: Qiangfei Xia, Ph.D. Joshua Yang, Ph.D. CONTACT: Neuromorphic computing, systems designed to mimic the biological nervous system, require far less power than current computer processors. The increased efficiency makes feasible artificial intelligence applications for smaller, hand-held devices (e.g. smartphones, tablets). To this end, UMass inventors have designed hardware components that mimic neuronal synapses (Figure A). Specifically, diffusive Ag-in-oxide memristors show a temporal response during and after stimulation similar to that of a biological synapse. The novel diffusive memristor and its synapse-like dynamics enable a direct emulation of both short- and long-term plasticity of biological synapses and represent a major advancement in a hardware implementation for neuromorphic computing.
USA