A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses

Implementing compact, low-power artificial neural processing systems with real-time on-line learning abilities is still an open challenge. In this paper we present a full-custom mixed-signal VLSI device with neuromorphic learning circuits that emulate the biophysics of real spiking neurons and dynamic synapses for exploring the properties of computational neuroscience models and for building brain-inspired computing systems. The proposed architecture allows the on-chip configuration of a wide range of network connectivities, including recurrent and deep networks, with short-term and long-term plasticity. The device comprises 128 K analog synapse and 256 neuron circuits with biologically plausible dynamics and bi-stable spike-based plasticity mechanisms that endow it with on-line learning abilities. In addition to the analog circuits, the device comprises also asynchronous digital logic circuits for setting different synapse and neuron properties as well as different network configurations. This prototype device, fabricated using a 180 nm 1P6M CMOS process, occupies an area of 51.4 mm2, and consumes approximately 4 mW for typical experiments, for example involving attractor networks. Here we describe the details of the overall architecture and of the individual circuits and present experimental results that showcase its potential. By supporting a wide range of cortical-like computational modules comprising plasticity mechanisms, this device will enable the realization of intelligent autonomous systems with on-line learning capabilities.

• Publication year

  2015

• Venue

  Frontiers in Neuroscience

• Publication date

  2015-04-29

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.3389/fnins.2015.00141PMID 25972778PMCID 4413675
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Characterization and Compensation of Network-Level Anomalies in Mixed-Signal Neuromorphic Modeling Platforms

  2014cited by this paper
• Narrow linewidth two-electrode 1560 nm laterally coupled distributed feedback lasers with third-order surface etched gratings.

  2014cited by this paper
• The SpiNNaker Project

  2014cited by this paper
• Ultra low leakage synaptic scaling circuits for implementing homeostatic plasticity in neuromorphic architectures

  2014cited by this paper
• Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations

  2014cited by this paper
• A neuromorphic network for generic multivariate data classification

  2014influential reference
• A million spiking-neuron integrated circuit with a scalable communication network and interface

  2014cited by this paper
• Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems

  2014cited by this paper
• Minitaur, an Event-Driven FPGA-Based Spiking Network Accelerator

  2014cited by this paper
• PyNCS: a microkernel for high-level definition and configuration of neuromorphic electronic systems

  2014cited by this paper
• Spatio-temporal Spike Pattern Classification in Neuromorphic Systems

  2013cited by this paper
• An FPGA Implementation of a Polychronous Spiking Neural Network with Delay Adaptation

  2013cited by this paper
• The Sparseness of Mixed Selectivity Neurons Controls the Generalization–Discrimination Trade-Off

  2013cited by this paper
• Neuron Array With Plastic Synapses and Programmable Dendrites

  2013influential reference
• Robotic goalie with 3 ms reaction time at 4% CPU load using event-based dynamic vision sensor

  2013cited by this paper
• Boosting: Foundations and Algorithms

  2013cited by this paper
• Synthesizing cognition in neuromorphic electronic systems

  2013influential reference
• Real-time classification and sensor fusion with a spiking deep belief network

  2013cited by this paper
• Learning Hierarchical Features for Scene Labeling

  2013cited by this paper
• Acoustic Modeling Using Deep Belief Networks

  2012cited by this paper
• Exploiting device mismatch in neuromorphic VLSI systems to implement axonal delays

  2012cited by this paper
• VLSI Implementation of a Bio-Inspired Olfactory Spiking Neural Network

  2012cited by this paper
• Spike-Timing-Dependent Plasticity: A Comprehensive Overview

  2012cited by this paper
• 65k-neuron integrate-and-fire array transceiver with address-event reconfigurable synaptic routing

  2012cited by this paper
• Robust Working Memory in an Asynchronously Spiking Neural Network Realized with Neuromorphic VLSI

  2011cited by this paper
• A Simple Derivation of a Bound on the Perceptron Margin Using Singular Value Decomposition

  2011cited by this paper
• Neuromorphic Silicon Neuron Circuits

  2011cited by this paper
• Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System

  2011cited by this paper
• Building high-level features using large scale unsupervised learning

  2011cited by this paper
• A log-domain implementation of the Izhikevich neuron model

  2010influential reference
• Neuromorphic sensory systems.

  2010cited by this paper
• Attractor concretion as a mechanism for the formation of context representations

  2010cited by this paper
• A comprehensive workflow for general-purpose neural modeling with highly configurable neuromorphic hardware systems

  2010cited by this paper
• A log-domain implementation of the Mihalas-Niebur neuron model

  2010influential reference
• 32-bit Configurable bias current generator with sub-off-current capability

  2010cited by this paper
• Questions about STDP as a General Model of Synaptic Plasticity

  2010cited by this paper
• Control of GABA Release at Mossy Fiber-CA3 Connections in the Developing Hippocampus

  2010cited by this paper
• Competitive STDP-Based Spike Pattern Learning

  2009cited by this paper
• Adaptive exponential integrate-and-fire model

  2009cited by this paper
• Memory retention and spike-timing-dependent plasticity.

  2009cited by this paper
• STDP enables spiking neurons to detect hidden causes of their inputs

  2009cited by this paper
• On Real-Time AER 2-D Convolutions Hardware for Neuromorphic Spike-Based Cortical Processing

  2008cited by this paper
• State-Dependent Computation Using Coupled Recurrent Networks

  2008cited by this paper
• A VLSI network of spiking neurons with plastic fully configurable “stop-learning” synapses

  2008cited by this paper
• Learning Real-world Stimuli in a Neural Network with Spike-driven Synaptic Dynamics Intrinsic Mechanisms for Adaptive Gain Rescaling in Barrel Cortex Dynamic I-v Curves Are Reliable Predictors of Naturalistic Pyramidal-neuron Voltage Boundary in Conductance Space Two Computational Regimes of a Singl

  2008influential reference
• A Spatial Contrast Retina With On-Chip Calibration for Neuromorphic Spike-Based AER Vision Systems

  2007cited by this paper
• Synaptic Dynamics in Analog VLSI

  2007influential reference
• Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic Dynamics

  2007cited by this paper
• Thermodynamically Equivalent Silicon Models of Voltage-Dependent Ion Channels

  2007influential reference
• Stochastic Synapse with Short-Term Depression for Silicon Neurons

  2007cited by this paper
• A selective attention multi--chip system with dynamic synapses and spiking neurons

  2006influential reference
• A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity

  2006influential reference
• Reconfigurable Asynchronous Logic

  2006cited by this paper
• Adaptive exponential integrate-and-fire model as an effective description of neuronal activity.

  2005cited by this paper
• Learning Only When Necessary: Better Memories of Correlated Patterns in Networks with Bounded Synapses

  2005cited by this paper
• Adaptive Exponential Integrate-and-Fire Model as an Effective Description of Neuronal Activity

  2005cited by this paper
• A bio-physically inspired silicon neuron

  2004influential reference
• Optic nerve signals in a neuromorphic chip II: testing and results

  2004cited by this paper
• Optic nerve signals in a neuromorphic chip I: Outer and inner retina models

  2004cited by this paper
• Modeling Short-Term Synaptic Depression in Silicon

  2003cited by this paper
• Simple model of spiking neurons

  2003cited by this paper
• Spike-Driven Synaptic Dynamics Generating Working Memory States

  2003cited by this paper
• Modelling the formation of working memory with networks of integrate-and-fire neurons connected by plastic synapses.

  2003influential reference
• On the design and characterization of femtoampere current-mode circuits

  2003cited by this paper
• EURASIP Journal on Applied Signal Processing 2003:7, 620–628 c ○ 2003 Hindawi Publishing Corporation Analog VLSI Circuits for Short-Term Dynamic Synapses

  2002cited by this paper
• Beyond spike timing: the role of nonlinear plasticity and unreliable synapses

  2002cited by this paper
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations

  2002cited by this paper
• OF LEARNING

  2002cited by this paper
• Analog VLSI: Circuits and Principles

  2002cited by this paper
• Silicon synaptic depression

  2001cited by this paper
• Random Forests

  2001cited by this paper
• Synaptic plasticity: taming the beast

  2000cited by this paper
• Point-to-point connectivity between neuromorphic chips using address events

  2000cited by this paper
• Analog very large-scale integrated (VLSI) implementation of a model of amplitude-modulation sensitivity in the auditory brainstem.

  1999cited by this paper
• A pulse-coded communications infrastructure for neuromorphic systems

  1999cited by this paper
• Synaptic Basis of Cortical Persistent Activity: the Importance of NMDA Receptors to Working Memory

  1999cited by this paper
• The Design

  1998cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper
• Sparse coding with an overcomplete basis set: a strategy employed by V1?

  1997cited by this paper
• An analog VLSI cochlea with new transconductance amplifiers and nonlinear gain control

  1996cited by this paper
• Suppression of the magnocellular pathway during saccades.

  1996cited by this paper
• Neuromorphic analogue VLSI.

  1995cited by this paper
• A silicon neuron

  1991influential reference
• Modeling brain function: the world of attractor neural networks, 1st Edition

  1989cited by this paper
• Neuromorphic Processor

  year unknowncited by this paper

• Thriving in-memory computing and neuromorphic applications of ferroelectric-based devices

  2026cites this paper
• A Unidirectional Two-Compartment Neuron Circuit with On-chip STDP learning

  2026cites this paper
• 3-dimensional multistate memristor structures based neuromorphic devices for high-density in-memory computing

  2026cites this paper
• Photonically linked three-dimensional neural networks based on memristive blinking neurons

  2026cites this paper
• Reservoir Computing: Foundations, Advances, and Challenges Toward Neuromorphic Intelligence

  2026influential citation
• Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimization

  2026cites this paper
• Feedback neurons based on perovskite memristor with nickel single-atom engineered reduced graphene oxide cathode.

  2026cites this paper
• Technology Roadmap of Bioinspired Computing Hardware.

  2026cites this paper
• A New Era in Computing: A Review of Neuromorphic Computing Chip Architecture and Applications

  2026cites this paper
• Spiking neural networks with fatigue spike-timing-dependent plasticity learning using hybrid memristor arrays

  2026cites this paper
• Advancing neuroengineering with Neuromorphic Twins

  2026cites this paper
• Error Amplification Limits ANN-to-SNN Conversion in Continuous Control

  2026cites this paper
• LitSpikingNet: A Lightweight Attention-Enhanced Spiking Neural Network for Medical Image Classification

  2025cites this paper
• A Comprehensive Review of Brain-inspired Navigation

  2025cites this paper
• Spike-based neuromorphic computing: An overview from bio-inspiration to hardware architectures and learning mechanisms

  2025cites this paper
• TaiBai: A fully programmable brain-inspired processor with topology-aware efficiency

  2025cites this paper
• Energy-Efficient Eimeria Parasite Detection Using a Two-Stage Spiking Neural Network Architecture

  2025influential citation
• Efficient ANN-SNN Conversion with Error Compensation Learning

  2025cites this paper
• Analog VLSI Implementation of Subthreshold Spiking Neural Networks and Its Application to Reservoir Computing

  2025cites this paper
• Synaptic Function in Memristor Devices for Neuromorphic Circuit Applications

  2025cites this paper
• CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement Learning

  2025cites this paper
• Two-Dimensional Materials for Brain-Inspired Computing Hardware.

  2025cites this paper
• Exploring Hybrid FitzHugh-Rinzel (FHR) Neuron Model Behavior: Cost-Effective FPGA Implementation for High-Frequency and High-Precision Matching by Electromagnetic Flux Effects

  2025cites this paper
• A neuromorphic processor with on-chip learning for beyond-CMOS device integration

  2025cites this paper
• ChronoPlastic Spiking Neural Networks

  2025cites this paper
• Bayesian electronics for trustworthy artificial intelligence

  2025cites this paper
• Ferroelectric Devices for Artificial Intelligence Chips

  2025cites this paper
• Neuromorphic Computing Chips: Challenges and Trends

  2025cites this paper
• Weight transport through spike timing for robust local gradients

  2025cites this paper
• Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks

  2025cites this paper
• NeuroPong: the event-based camera driven embedded neuromorphic system

  2025cites this paper
• Bioinspired recognition of cricket calling songs in sub-nanowatt inter-pulse delay detector

  2025cites this paper
• Biologically Realistic Computational Primitives of Neocortex Implemented on Neuromorphic Hardware Improve Vision Transformer Performance

  2025cites this paper
• A 0.96 pJ/SOP Heterogeneous Neuromorphic Chip Toward Energy-Efficient Edge Visual Applications

  2025cites this paper
• Digital Implementation of a Spiking/Bursting Neuron Model with Low Resources

  2025cites this paper
• Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control

  2025cites this paper
• Integrated artificial neurons from metal halide perovskites

  2025cites this paper
• Wandering around: a bioinspired approach to visual attention through object motion sensitivity

  2025cites this paper
• TS-SNN: Temporal Shift Module for Spiking Neural Networks

  2025influential citation
• Head-Tail-Aware KL Divergence in Knowledge Distillation for Spiking Neural Networks

  2025influential citation
• Biologically-Inspired Self-Tuning Neuromorphic PID Control for Real-Time Trajectory Tracking of a UAS

  2025cites this paper
• A canonical cortical electronic circuit for neuromorphic intelligence

  2025cites this paper
• Biohybrid Computing with Proteinoids and Algae

  2025cites this paper
• A Novel Time‐Division Multiplexing Architecture Revealed by Reconfigurable Synapse for Deep Neural Networks

  2025cites this paper
• A Novel Ferroelectric MemCapacitor Enabling Multilevel Operation

  2025cites this paper
• An Analysis of Components and Enhancement Strategies for Advancing Memristive Neural Networks

  2025cites this paper
• Carbon-based iontronics – current state and future perspectives

  2025cites this paper
• Space-Time Smooth Control of Closed-Loop Neuromorphic Robotic Arms Using Spiking Neural Networks

  2025cites this paper
• Cloud Computing Framework based on Quantum-Neuromorphic Technology

  2025cites this paper
• Biological fidelity: The engine driving the neuromorphic renaissance.

  2025cites this paper
• Automatic generation of spiking neural networks on neuromorphic computing hardware for IoT edge computing

  2025cites this paper
• Neuromorphic algorithms for brain implants: a review

  2025cites this paper
• STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks

  2025influential citation
• Secondary Order RC Sensor Neuron Circuit for Direct Input Encoding in Spiking Neural Network

  2024cites this paper
• NeuroREC: A 28-nm Efficient Neuromorphic Processor for Radar Emitter Classification

  2024cites this paper
• A lightweight data-driven spiking neuronal network model of Drosophila olfactory nervous system with dedicated hardware support

  2024cites this paper
• MorphBungee: A 65-nm 7.2-mm2 27-µJ/Image Digital Edge Neuromorphic Chip With on-Chip 802-Frame/s Multi-Layer Spiking Neural Network Learning

  2024cites this paper
• Toward Efficient System-on-Module for Design-Space Exploration of Analog Spiking Neural Networks

  2024cites this paper
• Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework

  2024cites this paper
• Synchronized stepwise control of firing and learning thresholds in a spiking randomly connected neural network toward hardware implementation

  2024cites this paper
• Enhancing Training of Spiking Neural Network with Stochastic Latency

  2024cites this paper
• Spiking-NeRF: Spiking Neural Network for Energy-Efficient Neural Rendering

  2024cites this paper
• Direct training high-performance deep spiking neural networks: a review of theories and methods

  2024cites this paper
• Neuron Circuit Based on a Split-gate Transistor with Nonvolatile Memory for Homeostatic Functions of Biological Neurons

  2024cites this paper
• Hardware for Deep Learning Acceleration

  2024cites this paper
• Photonic-electronic spiking neuron with multi-modal and multi-wavelength excitatory and inhibitory operation for high-speed neuromorphic sensing and computing

  2024cites this paper
• Novel Three-Dimensional Artificial Neural Network Based on an Eight-Layer Vertical Memristor with an Ultrahigh Rectify Ratio (>107) and an Ultrahigh Nonlinearity (>105) for Neuromorphic Computing.

  2024cites this paper
• Vertically Stackable Ovonic Threshold Switch Oscillator Using Atomic Layer Deposited Ge0.6Se0.4 Film for High-Density Artificial Neural Networks.

  2024cites this paper
• Toward a Brain–Neuromorphics Interface

  2024cites this paper
• A 0.67-to-5.4 TSOPs/W Spiking Neural Network Accelerator With 128/256 Reconfigurable Neurons and Asynchronous Fully Connected Synapses

  2024cites this paper
• Brain-Inspired Computing: A Systematic Survey and Future Trends

  2024influential citation
• TEXEL: A neuromorphic processor with on-chip learning for beyond-CMOS device integration

  2024cites this paper
• Memristor‐Based Neuromorphic Chips

  2024cites this paper
• Continual Learning With Neuromorphic Computing: Foundations, Methods, and Emerging Applications

  2024cites this paper
• DS-CIM: A 40nm Asynchronous Dual-Spike Driven, MRAM Compute-In-Memory Macro for Spiking Neural Network

  2024cites this paper
• Hybrid CMOS LIF Neuron and Memristor Array System for Visual Pattern Recognition

  2024cites this paper
• From the Pursuit of Universal AGI Architecture to Systematic Approach to Heterogenous AGI: Addressing Alignment, Energy, & AGI Grand Challenges

  2024cites this paper
• Adiabatic leaky integrate and fire neurons with refractory period for ultra low energy neuromorphic computing

  2024cites this paper
• Event-Driven Frequency Decomposition with Spiking Phase-Locked Loops

  2024cites this paper
• Fused-MemBrain: a spiking processor combining CMOS and self-assembled memristive networks

  2024cites this paper
• Spike-HAR++: an energy-efficient and lightweight parallel spiking transformer for event-based human action recognition

  2024cites this paper
• Rearchitecting a Neuromorphic Processor for Spike-Driven Brain-Computer Interfacing

  2024cites this paper
• Scalable Microscale Artificial Synapses of Lead Halide Perovskite with Femtojoule Energy Consumption

  2024cites this paper
• Multiplierless Implementation of Fitz-Hugh Nagumo (FHN) Modeling Using CORDIC Approach

  2024cites this paper
• Fullerene-Inspired Efficient Neuromorphic Network-on-Chip Scheme

  2024cites this paper
• NeoHebbian synapses to accelerate online training of neuromorphic hardware

  2024cites this paper
• Continual Learning with Neuromorphic Computing: Theories, Methods, and Applications

  2024cites this paper
• Spike-based computational primitives to reproduce neural dynamics in the parietal cortex during motor preparation

  2024cites this paper
• Analog Sequential Hippocampal Memory Model for Trajectory Learning and Recalling: A Robustness Analysis Overview

  2024cites this paper
• Event-Based Stereo Depth Estimation: A Survey

  2024cites this paper
• Analog Implementation of a Spiking System for Performing Arithmetic Logic Operations on Mixed‐Signal Neuromorphic Processors

  2024cites this paper
• A Nanoscale Bistable Resistor for an Oscillatory Neural Network.

  2024cites this paper
• Design of Mixed-Signal LSI with Analog Spiking Neural Network and Digital Inference Circuits for Reservoir Computing

  2024cites this paper
• Fully Spiking Actor Network With Intralayer Connections for Reinforcement Learning

  2024cites this paper
• Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications

  2024cites this paper
• Hardware-friendly implementation of physical reservoir computing with CMOS-based time-domain analog spiking neurons

  2024cites this paper
• Spike frequency adaptation: bridging neural models and neuromorphic applications

  2024cites this paper
• ANP-I: A 28-nm 1.5-pJ/SOP Asynchronous Spiking Neural Network Processor Enabling Sub-0.1-μ J/Sample On-Chip Learning for Edge-AI Applications

  2024cites this paper
• NEXUS: A 28nm 3.3pJ/SOP 16-Core Spiking Neural Network With a Diamond Topology for Real-Time Data Processing

  2024cites this paper
• Unsupervised Classification of Spike Patterns with the Loihi Neuromorphic Processor

  2024cites this paper