A Survey of Neuromorphic Computing and Neural Networks in Hardware
read the original abstract
Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture. This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine learning problems. The promise of the technology is to create a brain-like ability to learn and adapt, but the technical challenges are significant, starting with an accurate neuroscience model of how the brain works, to finding materials and engineering breakthroughs to build devices to support these models, to creating a programming framework so the systems can learn, to creating applications with brain-like capabilities. In this work, we provide a comprehensive survey of the research and motivations for neuromorphic computing over its history. We begin with a 35-year review of the motivations and drivers of neuromorphic computing, then look at the major research areas of the field, which we define as neuro-inspired models, algorithms and learning approaches, hardware and devices, supporting systems, and finally applications. We conclude with a broad discussion on the major research topics that need to be addressed in the coming years to see the promise of neuromorphic computing fulfilled. The goals of this work are to provide an exhaustive review of the research conducted in neuromorphic computing since the inception of the term, and to motivate further work by illuminating gaps in the field where new research is needed.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
UniSpike: Accelerating Spiking Neural Networks on Neuromorphic Systems via Eliminating Address Redundancy
UniSpike eliminates address redundancy in spike packets via co-design of scheduling, runtime assembly hardware, and SNN partitioning, reporting 1.93x average traffic reduction, 1.77x speedup, and 1.50x energy improvement.
-
A Neuromodulable Current-Mode Silicon Neuron for Robust and Adaptive Neuromorphic Systems
A novel current-mode silicon neuron supports robust neuromodulation adaptation with minimal complexity and demonstrates high robustness across currents and temperatures in 180 nm CMOS experiments.
-
Frozen Backpropagation: Relaxing Weight Symmetry in Deep Spiking Neural Networks
fBP trains SNNs with separate forward and feedback networks by freezing feedback weights periodically during updates, matching BP accuracy while cutting transport costs up to 10,000x via partial schemes.
-
Hyperdimensional Decoding of Spiking Neural Networks
SNN-HDC decoding delivers better accuracy, lower latency, and 1.24x-3.67x lower estimated energy than standard methods on DvsGesture and SL-Animals-DVS while detecting 100% of samples from an untrained class.
-
On-chip learning in a conventional silicon MOSFET based Analog Hardware Neural Network
SPICE simulations demonstrate on-chip learning in a fully connected neural network using conventional MOSFETs as synapses, achieving high accuracy on the Iris dataset with performance comparable to NVM-based systems.
-
Benchmarking Physical Performance of Neural Inference Circuits
Authors apply a consistent methodology to benchmark physical performance metrics across neural network architectures and device technologies, identifying promising combinations.
-
Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems
A position and survey paper that identifies convergence between neuroscience, AGI, and neuromorphic computing and outlines four key integration challenges.
-
A Quarter of a Century of Neuromorphic Architectures on FPGAs -- an Overview
A literature survey of FPGA-based digital neuromorphic architectures over 25 years that creates a taxonomy of architectural features, lists advantages and disadvantages, and identifies trends.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.