Real-time decoding of brain activity by embedded Spiking Neural Networks using OxRAM synapses

T. Werner (1) , D. Garbin (1) , E. Vianello (1) , O. Bichler (2) , D. Cattaert (3) , B. Yvert (4, 5) , B. de Salvo (1) , L. Perniola (1)

1 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
2 DACLE-LIST - Département d'Architectures, Conception et Logiciels Embarqués-LIST
3 UB - Université de Bordeaux
4 UGA [2016-2019] - Université Grenoble Alpes [2016-2019]
5 SCLIN - Clinatec - Centre de recherche biomédicale Edmond J.Safra

An innovative approach for decoding of brain signals based on Spiking Neural Networks is presented in this paper. Synapses are implemented by BEOL compatible oxide resistive RAM (OxRAM) devices providing low programming voltages (<2.5V) and currents (∼30μA). Spike-timing-dependent plasticity enables the network for autonomous online spike sorting of measured biological signals. Ultra-low synaptic power consumption in the range of 10nW, recognition rates around 90% and real-time functionality bear high potential for future healthcare applications.

Keywords: Brain computer interface; Decoding; Intelligent agents; Interfaces (computer); Neural networks; Reconfigurable hardware; RRAM; Signal processing; Neuromorphic computing; Programming voltage; Spike timing dependent plasticities; Spike-sorting; Spiking neural networks; Brain; Innovative approaches; Health care application; Biological signals

Domains: Engineering Sciences [physics]

T. Werner, D. Garbin, E. Vianello, O. Bichler, D. Cattaert, et al.. Real-time decoding of brain activity by embedded Spiking Neural Networks using OxRAM synapses. 2016 IEEE International Symposium on Circuits and Systems (ISCAS), May 2016, Montreal, Canada. pp.2318-2321, ⟨10.1109/ISCAS.2016.7539048⟩. ⟨cea-01817861⟩