Masatoshi Ishii
IBM Research - Tokyo, Japan
On-chip trainable spike-based neuromorphic core using phase change memory as synapse
Abstract
Biologically inspired spiking neural network (SNN) is one of the most attractive approaches for highly energy-efficient computing systems such as mobile and IoT. Since fully-parallelized multiply-accumulate arithmetic and on-chip learning using spike-timing-dependent plasticity can be efficiently performed with analog-weighted dense non-volatile memory (NVM) arrays, it is expected that the combination of SNN together with NVM and on-chip learning could potentially bring new capabilities to edge computing systems. Though various approaches using different types of NVMs are still on-going and active area of research, phase change memory is arguably one of the most mature and promising emerging-NVM technologies. In this talk, on-chip trainable spike-based neuromorphic core using phase change memory as synapses will be mainly discussed.
Biography
Masatoshi Ishii is a Research Staff Member at IBM Research - Tokyo. He joined IBM Japan in 1998, where he has been engaged in broad electrical engineering fields including printed circuit board development for ThinkPad, signal and power integrity simulation for memory interfaces and full custom circuit design for SRAM and CAM macros. His current research interests include neuromorphic chip design and hardware-aware neural network simulator development.