A 0.086-mm${}^2$ 12.7-pJ/SOP 64k-Synapse 256-Neuron Online-Learning Digital Spiking Neuromorphic Processor in 28nm CMOS

Abstract

Shifting computing architectures from von Neumann to event-based spiking neural networks (SNNs) uncovers new opportunities for low-power processing of sensory data in applications such as vision or sensorimotor control. Exploring roads toward cognitive SNNs requires the design of compact, low-power and versatile experimentation platforms with the key requirement of online learning in order to adapt and learn new features in uncontrolled environments. However, embedding online learning in SNNs is currently hindered by high incurred complexity and area overheads. In this work, we present ODIN, a 0.086-mm${}^2$ 64k-synapse 256-neuron online-learning digital spiking neuromorphic processor in 28nm FDSOI CMOS achieving a minimum energy per synaptic operation (SOP) of 12.7pJ. It leverages an efficient implementation of the spike-driven synaptic plasticity (SDSP) learning rule for high-density embedded online learning with only 0.68$\mu$m${}^2$ per 4-bit synapse. Neurons can be independently configured as a standard leaky integrate-and-fire (LIF) model or as a custom phenomenological model that emulates the 20 Izhikevich behaviors found in biological spiking neurons. Using a single presentation of 6k 16$\times$16 MNIST training images to a single-layer fully-connected 10-neuron network with on-chip SDSP-based learning, ODIN achieves a classification accuracy of 84.5% while consuming only 15nJ/inference at 0.55V using rank order coding. ODIN thus enables further developments toward cognitive neuromorphic devices for low-power, adaptive and low-cost processing.

arXiv comment(C) 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses. This document is the paper as accepted for publication in the IEEE Transactions on Biomedical Circuits and Systems journal, the fully-edited paper is available at https://ieeexplore.ieee.org/document/8528875

References in corpus (4)

• Memory and information processing in neuromorphic systems
• A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)
• Biologically Inspired Spiking Neurons : Piecewise Linear Models and Digital Implementation
• An Ultralow Leakage Synaptic Scaling Homeostatic Plasticity Circuit With Configurable Time Scales up to 100 ks

Cited by in corpus (31)

• Brain-inspired computing: We need a master plan
• Adaptive Extreme Edge Computing for Wearable Devices
• A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms
• Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence
• The importance of space and time in neuromorphic cognitive agents
• Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks
• Low-Power Low-Latency Keyword Spotting and Adaptive Control with a SpiNNaker 2 Prototype and Comparison with Loihi
• Spiker: an FPGA-optimized Hardware acceleration for Spiking Neural Networks
• Sparse Compressed Spiking Neural Network Accelerator for Object Detection
• Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
• Compiling Spiking Neural Networks to Neuromorphic Hardware
• ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories
• RANC: Reconfigurable Architecture for Neuromorphic Computing
• Spiker+: a framework for the generation of efficient Spiking Neural Networks FPGA accelerators for inference at the edge
• SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errors
• Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection
• An ultra-low-power sigma-delta neuron circuit
• Stochastic Domain Wall-Magnetic Tunnel Junction Artificial Neurons for Noise-Resilient Spiking Neural Networks
• EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems
• ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware
• Demonstrating Analog Inference on the BrainScaleS-2 Mobile System
• RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
• Neuromorphic analog circuits for robust on-chip always-on learning in spiking neural networks
• Special Session: Neuromorphic hardware design and reliability from traditional CMOS to emerging technologies
• An Inference and Learning Engine for Spiking Neural Networks in Computational RAM (CRAM)
• MC-QDSNN: Quantized Deep evolutionary SNN with Multi-Dendritic Compartment Neurons for Stress Detection using Physiological Signals
• QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models
• IzhiRISC-V -- a RISC-V-based Processor with Custom ISA Extension for Spiking Neuron Networks Processing with Izhikevich Neurons
• Non-uniform Memory Partitioning For Low-Power Spiking Neural Networks
• SpikeVox: Towards Energy-Efficient Speech Therapy Framework with Spike-driven Generative Language Models
• Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks