Memory and information processing in neuromorphic systems

Abstract

A striking difference between brain-inspired neuromorphic processors and current von Neumann processors architectures is the way in which memory and processing is organized. As Information and Communication Technologies continue to address the need for increased computational power through the increase of cores within a digital processor, neuromorphic engineers and scientists can complement this need by building processor architectures where memory is distributed with the processing. In this paper we present a survey of brain-inspired processor architectures that support models of cortical networks and deep neural networks. These architectures range from serial clocked implementations of multi-neuron systems to massively parallel asynchronous ones and from purely digital systems to mixed analog/digital systems which implement more biological-like models of neurons and synapses together with a suite of adaptation and learning mechanisms analogous to the ones found in biological nervous systems. We describe the advantages of the different approaches being pursued and present the challenges that need to be addressed for building artificial neural processing systems that can display the richness of behaviors seen in biological systems.

Submitted to Proceedings of IEEE, review of recently proposed neuromorphic computing platforms and systems

References in corpus (3)

• Deep Learning in Neural Networks: An Overview
• Training and Operation of an Integrated Neuromorphic Network Based on Metal-Oxide Memristors
• Six networks on a universal neuromorphic computing substrate

Cited by in corpus (74)

• SLIM: Simultaneous Logic-in-Memory Computing Exploiting Bilayer Analog OxRAM Devices
• Neuromorphic Silicon Photonic Networks
• A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)
• A 0.086-mm${}^2$ 12.7-pJ/SOP 64k-Synapse 256-Neuron Online-Learning Digital Spiking Neuromorphic Processor in 28nm CMOS
• Spiking Neural Networks Hardware Implementations and Challenges: a Survey
• Hardware Implementation of Deep Network Accelerators Towards Healthcare and Biomedical Applications
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• An electronic neuromorphic system for real-time detection of High Frequency Oscillations (HFOs) in intracranial EEG
• An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture
• A recipe for creating ideal hybrid memristive-CMOS neuromorphic computing systems
• Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence
• Ultra-Low-Power FDSOI Neural Circuits for Extreme-Edge Neuromorphic Intelligence
• A neuromorphic systems approach to in-memory computing with non-ideal memristive devices: From mitigation to exploitation
• The importance of space and time in neuromorphic cognitive agents
• Hydrophobically gated memristive nanopores for neuromorphic applications
• Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
• An event-based architecture for solving constraint satisfaction problems
• A spiking neuron constructed by the skyrmion-based spin torque nano-oscillator
• An atomic Boltzmann machine capable of on-chip learning
• Resonate and Fire Neuron with Fixed Magnetic Skyrmions
• Strain-engineered inverse charge-funnelling in layered semiconductors
• The complex dynamics of memristive circuits: analytical results and universal slow relaxation
• A differential memristive synapse circuit for on-line learning in neuromorphic computing systems
• Mem-fractive Properties of Mushrooms
• Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks
• The Free Energy Principle drives neuromorphic development
• Electric Field Driven Memristive Behavior at the Schottky Interface of Nb doped SrTiO3
• Hierarchical Short- and Medium-Range Order Structures in Amorphous GexSe1-x for Selectors Applications
• Neuromorphic Visual Scene Understanding with Resonator Networks
• Integration of Neuromorphic AI in Event-Driven Distributed Digitized Systems: Concepts and Research Directions
• Locality of interactions for planar memristive circuits
• Ferroelectric Tunneling Junctions for Edge Computing
• Asymptotic behavior of memristive circuits
• Mimicking synaptic plasticity with wedged Pt/Co/Pt spin-orbit torque device
• Synaptic Delays for Temporal Feature Detection in Dynamic Neuromorphic Processors
• Prominent characteristics of recurrent neuronal networks are robust against low synaptic weight resolution
• Modelling Reservoir Computing with the Discrete Nonlinear Schrödinger Equation
• Highly Reproducible and CMOS-compatible VO2-based Oscillators for Brain-inspired Computing
• Understanding Memristive Behavior: An Atomistic Study of the Influence of Grain Boundaries on Surface and Out-of-Plane Diffusion of Metallic Atoms
• Memristive Networks: from Graph Theory to Statistical Physics
• Vector Symbolic Finite State Machines in Attractor Neural Networks
• Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses
• The mise en scene of memristive networks: effective memory, dynamics and learning
• Visual Odometry with Neuromorphic Resonator Networks
• Quantum Computing and Neuromorphic Computing for Safe, Reliable, and explainable Multi-Agent Reinforcement Learning: Optimal Control in Autonomous Robotics
• Improvement of FTJ on-current by work function engineering for massive parallel neuromorphic computing
• Precise neural network computation with imprecise analog devices
• Fatiguing STDP: Learning from Spike-Timing Codes in the Presence of Rate Codes
• A mean-field model of memristive circuit interaction
• Semi-Trained Memristive Crossbar Computing Engine with In-Situ Learning Accelerator
• Spike-based primitives for graph algorithms
• Sparse Spiking Gradient Descent
• Scaling mixed-signal neuromorphic processors to 28 nm FD-SOI technologies
• Hyperchaos and complex dynamical regimes in $N$-dimensional neuron lattices
• Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking Neurons
• Holographic photonic neuron
• Generic Wave Digital Emulation of Memristive Devices
• Numerical study of synaptic behavior in amorphous HfO2-based ferroelectric-like FETs generated by voltage-driven ion migration
• Benchmarking Physical Performance of Neural Inference Circuits
• A 120dB Programmable-Range On-Chip Pulse Generator for Characterizing Ferroelectric Devices
• Heterogeneous Population Encoding for Multi-joint Regression using sEMG Signals
• Synaptic Integration of Spatiotemporal Features with a Dynamic Neuromorphic Processor
• Switching time of spin-torque-driven magnetization in biaxial ferromagnets
• A feedback control optimizer for online and hardware-aware training of Spiking Neural Networks
• On memfractance of plants and fungi
• Harnessing Slow Dynamics in Neuromorphic Computation
• Layer-wise synapse optimization for implementing neural networks on general neuromorphic architectures
• Spiking label propagation for community detection
• Artificial Retina Using A Hybrid Neural Network With Spatial Transform Capability
• 2022 Roadmap on Neuromorphic Computing and Engineering
• Sequence-SOD: Bio-inspired Sequence-aware Spiking ObjectDetection for Event Cameras
• Quantum-Inspired Computing: Can it be a Microscopic Computing Model of the Brain?
• Analog circuits for mixed-signal neuromorphic computing architectures in 28 nm FD-SOI technology
• Realization of A Non-Markov Chain in A Single 2D Crystal RRAM