The organization of behavior: A neuropsychological theory

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

A Survey of Neuromorphic Computing and Neural Networks in Hardware.

Spiking neural networks (SNNs) are inspired by information processing in biology, where sparse and asynchronous binary signals are communicated and processed in a massively parallel fashion. SNNs on neuromorphic hardware exhibit favorable properties such as low power consumption, fast inference, and event-driven information processing. This makes them interesting candidates for the efficient implementation of deep neural networks, the method of choice for many machine learning tasks. In this review, we address the opportunities that deep spiking networks offer and investigate in detail the challenges associated with training SNNs in a way that makes them competitive with conventional deep learning, but simultaneously allows for efficient mapping to hardware. A wide range of training methods for SNNs is presented, ranging from the conversion of conventional deep networks into SNNs, constrained training before conversion, spiking variants of backpropagation, and biologically motivated variants of STDP. The goal of our review is to define a categorization of SNN training methods, and summarize their advantages and drawbacks. We further discuss relationships between SNNs and binary networks, which are becoming popular for efficient digital hardware implementation. Neuromorphic hardware platforms have great potential to enable deep spiking networks in real-world applications. We compare the suitability of various neuromorphic systems that have been developed over the past years, and investigate potential use cases. Neuromorphic approaches and conventional machine learning should not be considered simply two solutions to the same classes of problems, instead it is possible to identify and exploit their task-specific advantages. Deep SNNs offer great opportunities to work with new types of event-based sensors, exploit temporal codes and local on-chip learning, and we have so far just scratched the surface of realizing these advantages in practical applications.

/pdf/deep-learning-with-spiking-neurons-opportunities-and-2tr71hy1eo.pdf

Deep Learning With Spiking Neurons: Opportunities and Challenges.

Non-volatile memories will play a decisive role in the next generation of digital technology. Flash memories are currently the key player in the field, yet they fail to meet the commercial demands of scalability and endurance. Resistive memory devices, and in particular memories based on low-cost, solution-processable and chemically tunable organic materials, are promising alternatives explored by the industry. However, to date, they have been lacking the performance and mechanistic understanding required for commercial translation. Here we report a resistive memory device based on a spin-coated active layer of a transition-metal complex, which shows high reproducibility (∼350 devices), fast switching (≤30 ns), excellent endurance (∼1012 cycles), stability (>106 s) and scalability (down to ∼60 nm2). In situ Raman and ultraviolet-visible spectroscopy alongside spectroelectrochemistry and quantum chemical calculations demonstrate that the redox state of the ligands determines the switching states of the device whereas the counterions control the hysteresis. This insight may accelerate the technological deployment of organic resistive memories.

Robust Resistive Memory Devices Using Solution-Processable Metal-Coordinated Azo-aromatics

Automatic License Plate Recognition via sliding-window darknet-YOLO deep learning

Neuromorphic computing technologies will be important for the future of computing, but much of the work in neuromorphic computing has focused on hardware development. Here, we review recent results in neuromorphic computing algorithms and applications. We highlight characteristics of neuromorphic computing technologies that make them attractive for the future of computing and we discuss opportunities for future development of algorithms and applications on these systems. There is still a wide variety of challenges that restrict the rapid growth of neuromorphic algorithmic and application development. Addressing these challenges is essential for the research community to be able to effectively use neuromorphic computers in the future. 

/pdf/opportunities-for-neuromorphic-computing-algorithms-and-mbiyytrk.pdf

Opportunities for neuromorphic computing algorithms and applications

Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization

Brain-inspired computing is attracting considerable attention because of its potential to solve a wide variety of data-intensive problems that are difficult for even state-of-the-art supercomputers to tackle. The ability of the human brain to process visual and audio inputs in real time and make complex logical decisions by consuming a mere 20 W makes it the most power-efficient computational engine known to man. While state-of-the-art digital complimentary metal-oxide-semiconductor (CMOS) technology permits the realization of individual devices and circuits that mimic the dynamics of neurons and synapses in the brain, emulating the immense parallelism and event-driven computational architecture in systems with comparable complexity and power budget as the brain, and in real time, remains a formidable challenge.

Building Brain-Inspired Computing Systems: Examining the Role of Nanoscale Devices

In this paper, we propose a Spin Transfer Torque RAM (STT-RAM) based neurosynaptic core to implement a hardware accelerator for Spiking Neural Networks (SNNs), which mimic the time-based signal encoding and processing mechanisms of the human brain. The computational core consists of a crossbar array of non-volatile STT-RAMs, read/write peripheral circuits, and digital logic for the spiking neurons. Inter-core communication is realized through on-chip routing network by sending/receiving spike packets. Unlike prior works that use multi-level states of non-volatile memory (NVM) devices for the synaptic weights, we use the technologically-mature STT-RAM devices for binary data storage. The design studies are conducted using a compact model for STT-RAM devices, tuned to capture the state-of-the-art experimental results. Our design avoids the need for expensive ADCs and DACs, enabling instantiation of large NVM arrays for our core. We show that the STT-RAM based neurosynaptic core designed in 28 nm technology node has approximately 6× higher throughput per unit Watt and unit area than an equivalent SRAM based design. Our design also achieves ∼ 2× higher performance per Watt compared to other memristive neural network accelerator designs in the literature.

Neuromorphic Hardware Accelerator for SNN Inference based on STT-RAM Crossbar Arrays

Spiking Neural Networks (SNNs) are the third generation of artificial neural networks that closely mimic the time encoding and information processing aspects of the human brain. It has been postulated that these networks are more efficient for realizing cognitive computing systems compared to second generation networks that are widely used in machine learning algorithms today. In this paper, we review the learning algorithms, hardware demonstrations and potential applications of SNN based learning systems.

Shruti R. Kulkarni

Papers

Opportunities for neuromorphic computing algorithms and applications

Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization

Building Brain-Inspired Computing Systems: Examining the Role of Nanoscale Devices

Neuromorphic Hardware Accelerator for SNN Inference based on STT-RAM Crossbar Arrays

Spiking neural networks — Algorithms, hardware implementations and applications