Edge learning using a fully integrated neuro-inspired memristor chip

Reservoir computing with a random memristor crossbar array

Physical implementations of reservoir computing (RC) based on the emerging memristors have become promising candidates of unconventional computing paradigms. Traditionally, sequential approaches by time-multiplexing volatile memristors have been prevalent because of their low hardware overhead. However, they suffer from the problem of speed degradation and fall short of capturing the spatial relationship between the time-domain inputs. Here, we explore a new avenue for RC using memristor crossbar arrays with device-to-device variations, which serve as physical random weight matrices of the reservoir layers, enabling faster computation thanks to the parallelism of matrix-vector multiplication as an intensive operation in RC. To achieve this new RC architecture, ultralow-current, self-selective memristors are fabricated and integrated without the need of transistors, showing greater potential of high scalability and three-dimensional integrability compared to the previous realizations. The information processing ability of our RC system is demonstrated in asks of recognizing digit images and waveforms. This work indicates that the 'nonidealities' of the emerging memristor devices and circuits are a useful source of inspiration for new computing paradigms.

Proton Conducting Neuromorphic Materials and Devices

Neuromorphic computing and artificial intelligence hardware generally aims to emulate features found in biological neural circuit components and to enable the development of energy-efficient machines. In the biological brain, ionic currents and temporal concentration gradients control information flow and storage. It is therefore of interest to examine materials and devices for neuromorphic computing wherein ionic and electronic currents can propagate. Protons being mobile under an external electric field offers a compelling avenue for facilitating biological functionalities in artificial synapses and neurons. In this review, we first highlight the interesting biological analog of protons as neurotransmitters in various animals. We then discuss the experimental approaches and mechanisms of proton doping in various classes of inorganic and organic proton-conducting materials for the advancement of neuromorphic architectures. Since hydrogen is among the lightest of elements, characterization in a solid matrix requires advanced techniques. We review powerful synchrotron-based spectroscopic techniques for characterizing hydrogen doping in various materials as well as complementary scattering techniques to detect hydrogen. First-principles calculations are then discussed as they help provide an understanding of proton migration and electronic structure modification. Outstanding scientific challenges to further our understanding of proton doping and its use in emerging neuromorphic electronics are pointed out.

Memristive Characteristics in an Asymmetrically Charged Nanochannel

The emergent nanofluidic memristor provides a promising way of emulating neuromorphic functions in the brain. The conical-shaped nanopore showed promising features for a nanofluidic memristor, inspiring us to investigate the memory effects in asymmetrically charged nanochannels due to their high current rectification, which may result in good memory effects. Here, the memory effects of an asymmetrically charged nanofluidic channel were numerically simulated by Poisson-Nernst-Planck equations. Our results showed that the I-V curves represented a diode in low scanning frequency and then became a memristor and finally a resistor as frequency increased. We successfully replicated the learning behavior in our system with history-dependent ion redistribution in the nanochannel. Some critical factors were quantitatively analyzed for the memory effects including voltage amplitude, optimal frequency, and Dukhin number. Experimental characterizations were also carried out. Our findings are useful for the design of nanofluidic memristors by the principle of enrichment and depletion as well as the determination of the best memory settings.

A reversible implantable memristor for health monitoring applications

Conventional implantable electronics based on von Neumann architectures encounter significant limitations in computing and processing vast biological information due to computational bottlenecks. The memristor with integrated memory-computing and low power consumption offer a promising solution to overcome the computational bottleneck and Moore's law limitations of traditional silicon-based implantable devices, making them the most promising candidates for next-generation implantable devices. In this work, a highly stable memristor with an Ag/BaTiO3/MnO2/FTO structure was fabricated, demonstrating retention characteristics exceeding 1200 cycles and endurance above 1000 s. The device successfully exhibited three-stage responses to biological signals after implantation in SD (Sprague-Dawley) rats. Importantly, the memristor perform remarkable reversibility, maintaining over 100 cycles of stable repetition even after extraction from the rat. This study provides a new perspective on the biomedical application of memristors, expanding the potential of implantable memristive devices in intelligent medical fields such as health monitoring and auxiliary diagnostics.

Synergistically Modulating Conductive Filaments in Ion-Based Memristors for Enhanced Analog In-Memory Computing

Memristors offer a promising solution to address the performance and energy challenges faced by conventional von Neumann computer systems. Yet, stochastic ion migration in conductive filament often leads to an undesired performance tradeoff between memory window, retention, and endurance. Herein, a robust memristor based on oxygen-rich SnO2 nanoflowers switching medium, enabled by seed-mediated wet chemistry, to overcome the ion migration issue for enhanced analog in-memory computing is reported. Notably, the interplay between the oxygen vacancy (Vo) and Ag ions (Ag+) in the Ag/SnO2/p++-Si memristor can efficiently modulate the formation and abruption of conductive filaments, thereby resulting in a high on/off ratio (>106), long memory retention (10-year extrapolation), and low switching variability (SV = 6.85%). Multiple synaptic functions, such as paired-pulse facilitation, long-term potentiation/depression, and spike-time dependent plasticity, are demonstrated. Finally, facilitated by the symmetric analog weight updating and multiple conductance states, a high image recognition accuracy of ≥ 91.39% is achieved, substantiating its feasibility for analog in-memory computing. This study highlights the significance of synergistically modulating conductive filaments in optimizing performance trade-offs, balancing memory window, retention, and endurance, which demonstrates techniques for regulating ion migration, rendering them a promising approach for enabling cutting-edge neuromorphic applications.

Organic Synaptic Transistors with Environmentally Friendly Core/Shell Quantum Dots for Wavelength-Selective Memory and Neuromorphic Functions

Organic transistors based on organic semiconductors together with quantum dots (QDs) are attracting more and more interest because both materials have excellent optoelectronic properties and solution processability. Electronics based on nontoxic QDs are highly desired considering the potential health risks but are limited by elevated surface defects, inadequate stability, and diminished luminescent efficiency. Herein, organic synaptic transistors based on environmentally friendly ZnSe/ZnS core/shell QDs with passivating surface defects are developed, exhibiting optically programmable and electrically erasable characteristics. The synaptic transistors feature linear multibit storage capability and wavelength-selective memory function with a retention time above 6000 s. Various neuromorphic applications, including memory enhancement, optical communication, and memory consolidation behaviors, are simulated. Utilizing an established neuromorphic model, accuracies of 92% and 91% are achieved in pattern recognition and complicated electrocardiogram signal processing, respectively. This research highlights the potential of environmentally friendly QDs in neuromorphic applications and health monitoring.

Controlling chaos using edge computing hardware

Machine learning provides a data-driven approach for creating a digital twin of a system - a digital model used to predict the system behavior. Having an accurate digital twin can drive many applications, such as controlling autonomous systems. Often, the size, weight, and power consumption of the digital twin or related controller must be minimized, ideally realized on embedded computing hardware that can operate without a cloud-computing connection. Here, we show that a nonlinear controller based on next-generation reservoir computing can tackle a difficult control problem: controlling a chaotic system to an arbitrary time-dependent state. The model is accurate, yet it is small enough to be evaluated on a field-programmable gate array typically found in embedded devices. Furthermore, the model only requires 25.0 ± 7.0 nJ per evaluation, well below other algorithms, even without systematic power optimization. Our work represents the first step in deploying efficient machine learning algorithms to the computing "edge."

A Spiking Artificial Vision Architecture Based on Fully Emulating the Human Vision

Intelligent vision necessitates the deployment of detectors that are always-on and low-power, mirroring the continuous and uninterrupted responsiveness characteristic of human vision. Nonetheless, contemporary artificial vision systems attain this goal by the continuous processing of massive image frames and executing intricate algorithms, thereby expending substantial computational power and energy. In contrast, biological data processing, based on event-triggered spiking, has higher efficiency and lower energy consumption. Here, this work proposes an artificial vision architecture consisting of spiking photodetectors and artificial synapses, closely mirroring the intricacies of the human visual system. Distinct from previously reported techniques, the photodetector is self-powered and event-triggered, outputting light-modulated spiking signals directly, thereby fulfilling the imperative for always-on with low-power consumption. With the spiking signals processing through the integrated synapse units, recognition of graphics, gestures, and human action has been implemented, illustrating the potent image processing capabilities inherent within this architecture. The results prove the 90% accuracy rate in human action recognition within a mere five epochs utilizing a rudimentary artificial neural network. This novel architecture, grounded in spiking photodetectors, offers a viable alternative to the extant models of always-on low-power artificial vision system.

Large-scale photonic chiplet Taichi empowers 160-TOPS/W artificial general intelligence

The pursuit of artificial general intelligence (AGI) continuously demands higher computing performance. Despite the superior processing speed and efficiency of integrated photonic circuits, their capacity and scalability are restricted by unavoidable errors, such that only simple tasks and shallow models are realized. To support modern AGIs, we designed Taichi-large-scale photonic chiplets based on an integrated diffractive-interference hybrid design and a general distributed computing architecture that has millions-of-neurons capability with 160-tera-operations per second per watt (TOPS/W) energy efficiency. Taichi experimentally achieved on-chip 1000-category-level classification (testing at 91.89% accuracy in the 1623-category Omniglot dataset) and high-fidelity artificial intelligence-generated content with up to two orders of magnitude of improvement in efficiency. Taichi paves the way for large-scale photonic computing and advanced tasks, further exploiting the flexibility and potential of photonics for modern AGI.

Inorganic Halide Perovskite Nanowires/Conjugated Polymer Heterojunction-Based Optoelectronic Synaptic Transistors for Dynamic Machine Vision

Inspired by the retina, artificial optoelectronic synapses have groundbreaking potential for machine vision. The field-effect transistor is a crucial platform for optoelectronic synapses that is highly sensitive to external stimuli and can modulate conductivity. On the basis of the decent optical absorption, perovskite materials have been widely employed for constructing optoelectronic synaptic transistors. However, the reported optoelectronic synaptic transistors focus on the static processing of independent stimuli at different moments, while the natural visual information consists of temporal signals. Here, we report CsPbBrI2 nanowire-based optoelectronic synaptic transistors to study the dynamic responses of artificial synaptic transistors to time-varying visual information for the first time. Moreover, on the basis of the dynamic synaptic behavior, a hardware system with an accuracy of 85% is built to the trajectory of moving objects. This work offers a new way to develop artificial optoelectronic synapses for the construction of dynamic machine vision systems.

A Fully-Integrated Memristor Chip for Edge Learning

The fully-integrated memristor chip for edge learning provides a solid foundation for neural network computation. The fully-integrated memristor chip enables efficient object recognition in noisy backgrounds while minimizing energy consumption. The computing-in-memory chip represents an innovative and interdisciplinary technology that extends beyond multiple research domains.

Memristor-Based Neuromorphic Chips

In the era of information, characterized by an exponential growth in data volume and an escalating level of data abstraction, there has been a substantial focus on brain-like chips, which are known for their robust processing power and energy-efficient operation. Memristors are widely acknowledged as the optimal electronic devices for the realization of neuromorphic computing, due to their innate ability to emulate the interconnection and information transfer processes witnessed among neurons. This review paper focuses on memristor-based neuromorphic chips, which provide an extensive description of the working principle and characteristic features of memristors, along with their applications in the realm of neuromorphic chips. Subsequently, a thorough discussion of the memristor array, which serves as the pivotal component of the neuromorphic chip, as well as an examination of the present mainstream neural networks, is delved. Furthermore, the design of the neuromorphic chip is categorized into three crucial sections, including synapse-neuron cores, networks on chip (NoC), and neural network design. Finally, the key performance metrics of the chip is highlighted, as well as the key metrics related to the memristor devices are employed to realize both the synaptic and neuronal components.

Cross-layer transmission realized by light-emitting memristor for constructing ultra-deep neural network with transfer learning ability

Deep neural networks have revolutionized several domains, including autonomous driving, cancer detection, and drug design, and are the foundation for massive artificial intelligence models. However, hardware neural network reports still mainly focus on shallow networks (2 to 5 layers). Implementing deep neural networks in hardware is challenging due to the layer-by-layer structure, resulting in long training times, signal interference, and low accuracy due to gradient explosion/vanishing. Here, we utilize negative ultraviolet photoconductive light-emitting memristors with intrinsic parallelism and hardware-software co-design to achieve electrical information's optical cross-layer transmission. We propose a hybrid ultra-deep photoelectric neural network and an ultra-deep super-resolution reconstruction neural network using light-emitting memristors and cross-layer block, expanding the networks to 54 and 135 layers, respectively. Further, two networks enable transfer learning, approaching or surpassing software-designed networks in multi-dataset recognition and high-resolution restoration tasks. These proposed strategies show great potential for high-precision multifunctional hardware neural networks and edge artificial intelligence.

Toward a Brain-Neuromorphics Interface

Brain-computer interfaces (BCIs) that enable human-machine interaction have immense potential in restoring or augmenting human capabilities. Traditional BCIs are realized based on complementary metal-oxide-semiconductor (CMOS) technologies with complex, bulky, and low biocompatible circuits, and suffer with the low energy efficiency of the von Neumann architecture. The brain-neuromorphics interface (BNI) would offer a promising solution to advance the BCI technologies and shape the interactions with machineries. Neuromorphic devices and systems are able to provide substantial computation power with extremely high energy-efficiency by implementing in-materia computing such as in situ vector-matrix multiplication (VMM) and physical reservoir computing. Recent progresses on integrating neuromorphic components with sensing and/or actuating modules, give birth to the neuromorphic afferent nerve, efferent nerve, sensorimotor loop, and so on, which has advanced the technologies for future neurorobotics by achieving sophisticated sensorimotor capabilities as the biological system. With the development on the compact artificial spiking neuron and bioelectronic interfaces, the seamless communication between a BNI and a bioentity is reasonably expectable. In this review, the upcoming BNIs are profiled by introducing the brief history of neuromorphics, reviewing the recent progresses on related areas, and discussing the future advances and challenges that lie ahead.

Memristor-based storage system with convolutional autoencoder-based image compression network

The exponential growth of various complex images is putting tremendous pressure on storage systems. Here, we propose a memristor-based storage system with an integrated near-storage in-memory computing-based convolutional autoencoder compression network to boost the energy efficiency and speed of the image compression/retrieval and improve the storage density. We adopt the 4-bit memristor arrays to experimentally demonstrate the functions of the system. We propose a step-by-step quantization aware training scheme and an equivalent transformation for transpose convolution to improve the system performance. The system exhibits a high (>33 dB) peak signal-to-noise ratio in the compression and decompression of the ImageNet and Kodak24 datasets. Benchmark comparison results show that the 4-bit memristor-based storage system could reduce the latency and energy consumption by over 20×/5.6× and 180×/91×, respectively, compared with the server-grade central processing unit-based/the graphics processing unit-based processing system, and improve the storage density by more than 3 times.

Low-dimensional nanostructures for monolithic 3D-integrated flexible and stretchable electronics

Flexible/stretchable electronics, which are characterized by their ultrathin design, lightweight structure, and excellent mechanical robustness and conformability, have garnered significant attention due to their unprecedented potential in healthcare, advanced robotics, and human-machine interface technologies. An increasing number of low-dimensional nanostructures with exceptional mechanical, electronic, and/or optical properties are being developed for flexible/stretchable electronics to fulfill the functional and application requirements of information sensing, processing, and interactive loops. Compared to the traditional single-layer format, which has a restricted design space, a monolithic three-dimensional (M3D) integrated device architecture offers greater flexibility and stretchability for electronic devices, achieving a high-level of integration to accommodate the state-of-the-art design targets, such as skin-comfort, miniaturization, and multi-functionality. Low-dimensional nanostructures possess small size, unique characteristics, flexible/elastic adaptability, and effective vertical stacking capability, boosting the advancement of M3D-integrated flexible/stretchable systems. In this review, we provide a summary of the typical low-dimensional nanostructures found in semiconductor, interconnect, and substrate materials, and discuss the design rules of flexible/stretchable devices for intelligent sensing and data processing. Furthermore, artificial sensory systems in 3D integration have been reviewed, highlighting the advancements in flexible/stretchable electronics that are deployed with high-density, energy-efficiency, and multi-functionalities. Finally, we discuss the technical challenges and advanced methodologies involved in the design and optimization of low-dimensional nanostructures, to achieve monolithic 3D-integrated flexible/stretchable multi-sensory systems.

In-memory analog solution of compressed sensing recovery in one step

Modern analog computing, by gaining momentum from nonvolatile resistive memory devices, deals with matrix computations. In-memory analog computing has been demonstrated for solving some basic but ordinary matrix problems in one step. Among the more complicated matrix problems, compressed sensing (CS) is a prominent example, whose recovery algorithms feature high-order matrix operations and hardware-unfriendly nonlinear functions. In light of the local competitive algorithm (LCA), here, we present a closed-loop, continuous-time resistive memory circuit for solving CS recovery in one step. Recovery of one-dimensional (1D) sparse signal and 2D compressive images has been experimentally demonstrated, showing elapsed times around few microseconds and normalized mean squared errors of 10-2. The LCA circuit is one or two orders of magnitude faster than conventional digital approaches. It also substantially outperforms other (electronic or exotically photonic) analog CS recovery methods in terms of speed, energy, and fidelity, thus representing a highly promising technology for real-time CS applications.