A Survey of Neuromorphic Computing and Neural Networks in Hardware

By Catherine D. Schuman, Thomas E. Potok, Robert M. Patton, J. Douglas Birdwell, Mark E. Dean, G. Rose, James S. Plank. arXiv.org, 2017

805 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/4246d60507e8164c55a8a5c0b402c5e786ddc70c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

A Survey of the Usages of Deep Learning for Natural Language Processing (2020, background): “While GPUs have significantly improved the ability to train deep networks, they are only a step in the right direction [276].”
Neuromorphic Spintronics (2020, background): “Magnetic tunnel junctions have several features that other technologies 8 , both existing and emerging, do not combine; e.g. , nonvolatility, outstanding read/write endurance, high-speed and CMOS-compatible-voltage operation capability, high scalability, and back-end-of-line compatibility.”
Neuromorphic nanoelectronic materials (2020, methodology): “layers are: (1) CNT sensors as input, (2) ReRAM for memory, (3) CNT FET logic, (4) silicon logic and (5) ultra-dense interconnects.”
The future of electronics based on memristive systems (2018, methodology): “A variety of approaches are being explored using different neuron, synapse and network models 42 .”
Survey of Machine Learning Accelerators (2020, background): “Schuman’s survey [14] provides a rich background of all of the significant efforts in the field over the past several decades.”
Photonic Organolead Halide Perovskite Artificial Synapse Capable of Accelerated Learning at Low Power Inspired by Dopamine‐Facilitated Synaptic Activity (2018, background): “Figure 5a shows an example of a single-layer artificial neural network for “3” input pattern recognition process.[47,48] This network consists of 784 input neurons (28 × 28 pattern) and 10 output neurons with full connection (784 × 10 = 7840) by an individual synapse that has its own synaptic weight”
Opportunities for neuromorphic computing algorithms and applications (2022, methodology): “2e)—is the most commonly implemented synaptic plasticity mechanism in neuromorphic literature 10 .”
A Survey on Federated Learning for Resource-Constrained IoT Devices (2021, neutral): “We refer the readers to [197] to get a better overview of this ﬁeld.”