Search

Generally, computer-science-oriented artificial neural networks (ANNs) and neuroscience-oriented spiking neural networks (SNNs) are two main approaches to develop brain-spired non von Neumann computing systems. The goal of exploring complex artificial intelligence (AI) systems demands general neuromorphic hardware platforms compatible with both of them. However, as a result of the obvious differences in their fundamental mathematical expression and coding scheme, many neuromorphic platforms or deep neural network (DNN) accelerators accommodate only one of them. This brief presents a reconfigurable scalable neuromorphic chip based on digital leaky integrate-and-fire (LIF) neuron model targeting low-cost large-scale systems. By unifying ANN and SNN paradigms within a LIF neuron framework with point-to-point (P2P) communication, the chip can accommodate most popular neural networks. The chip adopts distributed on-chip memory architecture with a capacity of 64K neurons and 64M synapses. It achieves a peak throughput of 12.29 GSOP/s at 1.2 V, 192MHz and peak energy efficiency of 2.64 pJ/SOP at 890 mV, 24MHz. The results of implementations of a spike-based spatio-temporal memory model and ternary-weight event-based convolutional neural networks (CNNs) demonstrate outstanding compatibility of the chip.

Recent years, spike-based neuron computing on scalable and event-based neuromorphic hardware has demonstrated impressive energy efficiency. In this paper, we propose a novel spiking scheme for 1-bit and 8-bit convolutional neural networks and a systematic mapping algorithm for their deployments on a digital neuromorphic ASIC, with which we can automatically partition input and output feature maps for a 1152*1024 crossbar computing element for a excellent resource efficiency. Experimental results on MNIST dataset show that we can achieve about 98.5% and 99.4% test accuracy for these two kinds of bitwidth networks respectively, while the chip can achieve nearly 863 and 174 images/sec real-time inference speed at 0.9 V, 252 MHz.

Binary neural networks (BNNs) - neural networks with binary {-1, +1} weights and activations at run-time, have attracted much attention in recent years, which drastically reduce resource requirement and power consumption with tolerable accuracy loss. While, spiking neural networks (SNNs) are designed as a brain-inspired computing model, which can be deployed on large-scale distributed and event-based neuromorphic hardware efficiently. To enable a conversion of above two, we develop a variant of BNNs which employ binary-valued {0, +1} activations and ternary-valued {-1, 0, +1} weights and achieve start-of-the-art classification accuracy across two standard vision datasets, even better than the previous proposals using BNNs or SNNs. Furtherly, we propose an effective configuration method for network deployment on our designed programmable neuro-synaptic system with only one timestep and milliwatt level power consumption.