Building block of a programmable neuromorphic substrate: A digital neurosynaptic core

作者：John V. Arthur, Paul Merolla, Filipp Akopyan, Rodrigo Álvarez, Andrew S. Cassidy, Shyamal Chandra, Steven K. Esser, Nabil Imam, W. P. Risk, Daniel Ben Dayan Rubin, Rajit Manohar, Dharmendra S. Modha · 年份：2012 · DOI：10.1109/ijcnn.2012.6252637 · 被引用次数：133 · 研究领域：Advanced Memory and Neural Computing、Neural dynamics and brain function、Neuroscience and Neural Engineering

The grand challenge of neuromorphic computation is to develop a flexible brain-inspired architecture capable of a wide array of real-time applications, while striving towards the ultra-low power consumption and compact size of biological neural systems. Toward this end, we fabricated a building block of a modular neuromorphic architecture, a neurosynaptic core. Our implementation consists of 256 integrate-and-fire neurons and a 1,024×256 SRAM crossbar memory for synapses that fits in 4.2mm2using a 45nm SOI process and consumes just 45pJ per spike. The core is fully configurable in terms of neuron parameters, axon types, and synapse states and its fully digital implementation achieves one-to-one correspondence with software simulation models. One-to-one correspondence allows us to introduce an abstract neural programming model for our chip, a contract guaranteeing that any application developed in software functions identically in hardware. This contract allows us to rapidly test and map applications from control, machine vision, and classification. To demonstrate, we present four test cases (i) a robot driving in a virtual environment, (ii) the classic game of pong, (iii) visual digit recognition and (iv) an autoassociative memory.