Top Research Papers on Neuromorphic Computing

Neuromorphic engineering aims to advance computing by mimicking the brain's efficient processing, where data is encoded as asynchronous temporal events. This eliminates the need for a synchronisation clock and minimises power consumption when no data is present. However, many benchmarks for neuromorphic algorithms primarily focus on spatial features, neglecting the temporal dynamics that are inherent to most sequence-based tasks. This gap may lead to evaluations that fail to fully capture the unique strengths and characteristics of neuromorphic systems. In this paper, we present NeuroMorse, a ...

This review summarizes CMOS-compatible neuromorphic devices and discusses their emulation of synaptic and neuronal functions as well as their applications in neuromorphic perception and computing.

To understand the theoretical underpinnings of the neuromorphic approach and predict the likelihood of its implementation within the next decade, it is vital to understand the rise of high performance and Quantum computing as promising alternatives.

A compact and versatile neuromorphic computing core that integrates 1K neurons and 1M synapses through 588 LUTs is built through the use of neuron multiplexing technology and weight clustering algorithm.

It is shown for a two qubit system that quantum gates can be learned as a change of parameters for neural network dynamics, and the proposal for probabilistic computing goes beyond Markov chains and is not based on transition probabilities.

Progress was made on both the hardware and software side of neuromorphic computing research setting the stage for future agile information systems.

The memristor-based neuromorphic system can offer extremely high computation parallelism, high resilience to process variations and transient run-time errors, and high power efficiency with ultra-low hardware cost and small footprint, and is fully compatible to the present-day CMOS fabrication process, demonstrating an excellent scalability.

An introduction to neuromorphic computing, why this and other novel new computing systems are needed, and what technologies currently exist in the neuro-morphic field are provided.

The conventional Von Neumann architecture is explored and its shortcomings are outlined; neuromorphic architecture as an alternative and its evolution are described; and the key challenges hindering neuromorphic computing development are addressed.

From the ancient Greeks comparing memory to a 'seal ring in wax,' to the 19th century brain as a 'telegraph switching circuit', to Freud's subconscious desires 'boiling over like a steam engine,' to a hologram, and finally, the computer.

A source of single photons that meets three important criteria for use in quantum-information systems has been unveiled in China by an international team of physicists.

The efforts on using a near-field coupling platform for developing optical non-von Neumann computing devices and integrating phase-change materials nonvolatile components can be devised which allow for implementing hardware mimics of neural tissue.

This work introduces SONIC, a software-defined hardware design methodology to make neuromorphic computing accessible to the general computing community, and evaluates SONIC using three spiking datasets.

A schematic illustration of the human neural brain system and memristor based electronic neuromorphic system and the basic mechanism of the typical memristors for neuromorphic computing system.

How magnetic tunnel junctions can serve as synapses and neurons, and how magnetic textures, such as domain walls and skyrmions, can function as neurons, are examined.

Mainly the neuromorphic computing focus on matching a human brain flexibility, efficency and ability to learn and grab the things from physical environment with the energy efficiency of human brain.

This perspective article discusses the different implementations of quantum neuromorphic networks with digital and analog circuits, highlight their respective advantages, and review exciting recent experimental results.

This tutorial will look at challenges of photonic information processing, describe photonic neural-network approaches, and offer a glimpse at this field's future.

A schematic illustration of the human neural brain system and memristor based electronic neuromorphic system and memristor based electronic neuromorphic system.

Welcome to 2018 and IEEE Micros 38th year, where there were special issues on cognitive architectures, architectures for the post-Moore era, Cool Chips and Hot Interconnects, and ultra-low-power processors.

This work presents an overview of early attempts made to study a neuromorphic approach in a space context at the European Space Agency's (ESA) Advanced Concepts Team (ACT).

The three-terminal electrochemical memory based on the redox transistor (RT) is introduced, which uses a gate to tune the red ox state of the channel and storage of information as a charge-compensated redox reaction in the bulk of the transistor enables high-density information storage.

Neuromorphic computation is based on memristors, which function equivalently to neurons in brain structures. These memristors can be made more efficient and tailored to neuromorphic devices by using ferroelastic domain boundaries as fast diffusion paths for ionic conduction, such as of oxygen, sodium, or lithium. In this paper, we show that the local memristor generates a second, unexpected feature, namely, weak magnetic fields that emerge from moving ferroelastic needle domains and vortices. The vortices appear near ferroelastic “junctions” that are common when the external stimulus is a comb...

A new design rule for developing a brain inspired computing system based on some recent findings in brain science is proposed and a neuromorphic chip, named `Tianji' chip is designed and fabricated.

Neuroscience is beginning to inspire a new generation of seeing machines that will help us to understand the world around us in a more holistic way.

Neuromorphe Systeme arbeiten nicht nach herkömmlicher Computerlogik, sondern orientieren sich an der Funktionsweise eines biologischen Gehirns. Dazu übertragen sie die Art, in der Neuronen im Gehirn organisiert sind und miteinander kommunizieren, auf Hardwareebene. Das Ergebnis soll eine neue Computing-Architektur sein, die besonders energieeffizient ist, die dynamisch arbeitet und gleichzeitig lernfähig ist. Diese Eigenschaften versprechen großes Potenzial, insbesondere am Edge und in der Cloud. Bevor neuromorphe Lösungen flächendeckend zum Einsatz kommen werden, ist noch ausführliche Grundla...

Demonstrating Advantages of Neuromorphic Computation: The goal of neuromorphic computation is to develop a substrate that mimics the brain and reproduces its capabilities in terms of efficient, adaptive and highly parallelized computation. In this pilot study we demonstrate and quantify these advantages regarding emulation speed, energy efficiency and robustness to noise. We use a prototype chip of the BrainScaleS 2 neuromorphic system to implement a reinforcement learning experiment that uses a biologically plausible learning rule, reward-modulated spike-timing-dependent plasticity, to learn ...

most

A team of researchers at Google's DeepMind Technologies has been working on a means to increase the capabilities of computers by combining aspects of data processing and artificial intelligence and have come up with what they are calling a differentiable neural computer (DNC).

This paper will focus on the neuromorphic electronics, especially on the Neuromorphic Computing of neurons, synapses circuits and the spike timing dependent plasticity (STDP) scheme in detail based on memristors.

We have demonstrated electrically-injected waveguide-coupled LEDs based on W centers in silicon for neuromorphic computing. We analyze the sources of loss in these LEDs and simulate new designs for scalable, waveguide-coupled devices with several orders of magnitude higher efficiency.

A model describing a photonic crystal III-V/Silicon nanolaser composed of two sections predicts an excitable dynamics mimicking a neuron-like response and is scalable and amenable to massive integration.

of

This work presents a neuromorphic metasurface which is designed to exploit elastic wave scattering to realize a physical computing environment and opens up new avenues in high performance mechanical computing.

This work proposes utilizing the F1Tenth platform as an evaluation task for neuromorphic computing, and presents a workflow with neuromorphic hardware, software, and training that can be used to develop a spiking neural network for neuromorph hardware deployment to perform autonomous racing.

Vertical-Cavity Surface-Emitting Lasers for high-speed and energy-efficiency systems for photonic neuromorphic computing yield excellent performance in complex processing tasks whilst benefitting from hardware-friendly implementations and full compatibility with optical communication technologies.

The aim of this paper is to describe the current principles and development of the neuromorphic computing technology, explore the potential examples of neuromorphic computing applications in smart agriculture, and consider the future development route of the neuromorphic computing in smart agriculture.

Percolation with plasticity systems that exhibit neuromorphic functionalities including multi-valued memory, random number generation, matrix-vector multiplication, and associative learning are introduced.

The last few decades have witnessed the rapid development of electronic computers relying on von Neumann architecture. However, due to the spatial separation of the memory unit from the computing processor, continuous data movements between them result in intensive time and energy consumptions, which unfortunately hinder the further development of modern computers. Inspired by biological brain, the in situ computing of memristor architectures, which has long been considered to hold unprecedented potential to solve the von Neumann bottleneck, provides an alternative network paradigm for the nex...

A review of diverse approaches to implement neuromorphic functionalities in novel hardware using magnetic elements, published during the last years underlines the possible applications of magnetic materials and nanostructures in neuromorphic systems.

This work considers a reservoir comprised of a single qudit ($d$-dimensional quantum system), and demonstrates a robust performance advantage compared to an analogous classical system accompanied by a clear improvement with Hilbert space dimension for two benchmark tasks.

The state‐of‐the‐art spintronic technologies, such as the magnetic tunnel junction, spin–orbit torque, domain wall propagation, magnetic skyrmions, and antiferromagnet, are highlighted and how they can used for artificial neurons and synapses in different artificial neural networks are discussed.

This paper will explore how technology options affect design choices, using both digital and analog circuit designs suitable for neural nets.

The journal ``Neuromorphic Computing and Engineering'' (NCE) has been launched to support this new community in this effort and provide a forum and repository for presenting and discussing its latest advances.

A very simple 4-terminal synapse structure based on gated Schottky diodes on silicon (FEMOD) with a ferroelectric layer is proposed which can achieve multiple heterosynaptic functions, including excitatory/ inhibitory post-synaptic current (EPSC/IPSC), paired-pulse facilitation/depression (PPF/PPD), long-term potentiation/ Depression (LTP/LTD), and biological neuron

The conclusion is that the neuromorphic computers will replace the conventional Von Neumann computers, boosting the further development in computing power, breaking its limit.

This paper presents the history, the need for Neuromorphic computing, the functionalities, the current projects, their main features and technical capabilities of Neuromorph computing.

This paper considers the interplay between algorithm and architecture advances and finds that cooperation can provide a much needed strategic advantage in the face of challenges for either spiking algorithms or spiking architectures to advance the field independently.

This paper describes a model of neuromorphic computation and state the assumptions that govern the computational complexity of neuromorph algorithms, and presents a theoretical framework to define the computational complexities of a neuromorphic algorithm.

In this paper, we highlight how computational properties of biological dendrites can be leveraged for neuromorphic applications. Specifically, we demonstrate analog silicon dendrites that support multiplication mediated by conductance-based input in an interception model inspired by the biological dragonfly. We also demonstrate spatiotemporal pattern recognition and direction selectivity using dendrites on the Loihi neuromorphic platform. These dendritic circuits can be assembled hierarchically as building blocks for classifying complex spatiotemporal patterns.