 Foto: Sabina Spiga, [courtesy CNR-IMM, IT] |
|
 - 16.12.2019 -
S3 SEMINAR Sabina Spiga
Date and Time: Monday December 16, 2019 - 12:00
Venue: S3 Seminar Room, Third Floor, Physics Building, FIM Department
Speaker: Sabina Spiga, CNR-IMM Agrate Brianza (IT)
Title: Memristive devices for brain inspired computing
Abstract: Memristive devices have been receiving an increasing interest for a wide range of applications, such as storage class memory, non-volatile logic switch, in-memory computing and neuromorphic computing. In particular, in bio-inspired systems, memristive devices can act as dispersed memory elements mimicking synapses in nervous systems, or as stochastic and non-linear elements in neuronal units. Among the proposed technologies, oxide-based memristors (also named resistance switching memory, RRAM) are based on redox reactions and electrochemical phenomena in oxides and are very promising because of low power consumption, fast switching times, scalability down to nm scale and CMOS compatibility. In our work, we focus on the switching dynamics of HfO2 RRAMs and on their implementation as electronic synapses in spiking neural networks (SNN). Our results show that the device conductance can be tuned in an analog fashion by using train of identical pulses, to emulate the biological potentiation (conductance increase) and depression (conductance decrease) processes, over several cycles. The update of the conductance values can be achieved by a spike timing and rate dependent plasticity mechanism, which is demonstrated also at hardware level, and can be exploited as learning rule in a SNN. Finally, the experimental data sets are used to simulate a fully connected winner-take-all spiking neural network with leaky integrate and fire neurons equipped with circuitry emulating the temporal dynamics of biological synapses.
Host: Arrigo Calzolari e-mail: arrigo.calzolari@nano.cnr.it
|