Experimental demonstration of a second-order memristor and its ability to biorealistically implement synaptic plasticity

Research and Development of Parameter Extraction Approaches for Memristor Models

Memristors are among the most promising devices for building neural processors and non-volatile memory. One circuit design stage involves modeling, which includes the option of memristor models. The most common approach is the use of compact models, the accuracy of which is often determined by the accuracy of their parameter extraction from experiment results. In this paper, a review of existing extraction methods was performed and new parameter extraction algorithms for an adaptive compact model were proposed. The effectiveness of the developed methods was confirmed for the volt-ampere characteristic of a memristor with a vertical structure: TiN/Hf_xAl_1-xO_y/HfO₂/TiN.

Signal Filtering Enabled by Spike Voltage-Dependent Plasticity in Metalloporphyrin-Based Memristors

Neural systems can selectively filter and memorize spatiotemporal information, thus enabling high-efficient information processing. Emulating such an exquisite biological process in electronic devices is of fundamental importance for developing neuromorphic architectures with efficient in situ edge/parallel computing, and probabilistic inference. Here a novel multifunctional memristor is proposed and demonstrated based on metalloporphyrin/oxide hybrid heterojunction, in which the metalloporphyrin layer allows for dual electronic/ionic transport. Benefiting from the coordination-assisted ionic diffusion, the device exhibits smooth, gradual conductive transitions. It is shown that the memristive characteristics of this hybrid system can be modulated by altering the metal center for desired metal-oxygen bonding energy and oxygen ions migration dynamics. The spike voltage-dependent plasticity stemming from the local/extended movement of oxygen ions under low/high voltage is identified, which permits potentiation and depression under unipolar different positive voltages. As a proof-of-concept demonstration, memristive arrays are further built to emulate the signal filtering function of the biological visual system. This work demonstrates the ionic intelligence feature of metalloporphyrin and paves the way for implementing efficient neural-signal analysis in neuromorphic hardware.

Composite Memristors by Nanoscale Modification of Hf/Ta Anodic Oxides

Composite memristors based on anodic oxidation of Hf superimposed on Ta thin films are studied. A layered structure is obtained by successive sputtering of Ta and Hf thin films. The deposition geometry ensured components' thickness gradient profiles (wedges) aligned in opposite directions. Anodization in citrate buffer electrolyte leads to a nanoscale columnar structuring of Ta₂O₅ in HfO₂ due to the higher electrical resistance of the latter. Following the less resistive path, the ionic current forces Ta oxide to locally grow toward the electrolyte interface according to the Rayleigh-Taylor principle. The obtained composite oxide memristive properties are studied as a function of the Hf/Ta thickness ratio. One pronounced zone prominent for memristive applications is found for ratios between 4 and 5. Here, unipolar and bipolar memristors are found, with remarkable endurance and retention capabilities. This is discussed in the frame of conductive filament formation preferentially along the interfaces between oxides.

Voltage-dependent plasticity of spin-polarized conductance in phenyl-based single-molecule magnetic tunnel junctions

Synaptic strengths between neurons in brain networks are highly adaptive due to synaptic plasticity. Spike-timing-dependent plasticity (STDP) is a form of synaptic plasticity induced by temporal correlations between the firing activity of neurons. The development of experimental techniques in recent years enabled the realization of brain-inspired neuromorphic devices. Particularly, magnetic tunnel junctions (MTJs) provide a suitable means for the implementation of learning processes in molecular junctions. Here, we first considered a two-neuron motif subjected to STDP. By employing theoretical analysis and computer simulations we showed that the dynamics and emergent structure of the motif can be predicted by introducing an effective two-neuron synaptic conductance. Then, we considered a phenyl-based single-molecule MTJ connected to two ferromagnetic (FM) cobalt electrodes and investigated its electrical properties using the non-equilibrium Green’s function (NEGF) formalism. Similar to the two-neuron motif, we introduced an effective spin-polarized conductance in the MTJ. Depending on the polarity, frequency and strength of the bias voltage applied to the MTJ, the system can learn input signals by adaptive changes of the effective conductance. Interestingly, this voltage-dependent plasticity is an intrinsic property of the MTJ where its behavior is reminiscent of the classical temporally asymmetric STDP. Furthermore, the shape of voltage-dependent plasticity in the MTJ is determined by the molecule-electrode coupling strength or the length of the molecule. Our results may be relevant for the development of single-molecule devices that capture the adaptive properties of synapses in the brain.

Near-Infrared Artificial Synapses for Artificial Sensory Neuron System

The computing based on artificial neuron network is expected to break through the von Neumann bottleneck of traditional computer, and to greatly improve the computing efficiency, displaying a broad prospect in the application of artificial visual system. In the specific structural layout, it is a common method to connect the discrete photodetector with the artificial neuron in series, which enhances the complexity of signal recognition, conversion and storage. In this work, organic small molecule IR-780 iodide is inserted into the memory device as both the charge trapping layer and near-infrared (NIR) photoresponsive film. Through electrical and optical regulation, artificial synaptic functions including short-term plasticity, long-term plasticity, and spike rate dependence are realized. In the established artificial sensory neuron system, NIR optical pulses can significantly improve the spiking rate. Moreover, the spiking neural networks are further constructed by simulation for handwritten digit classification. This research may contribute to the development of light driven neural robots, optical signal encryption, and neural computing.

Nanomaterials and their applications on bio-inspired wearable electronics

Wearable electronics featuring conformal attachment, sensitive perception and intellectual signal processing have made significant progress in recent years. However, when compared with living organisms, artificial sensory devices showed undeniable bulky shape, poor adaptability, and large energy consumption. To make up for the deficiencies, biological examples provide inspirations of novel designs and practical applications. In the field of biomimetics, nanomaterials from nanoparticles to layered two-dimensional materials are actively involved due to their outstanding physicochemical properties and nanoscale configurability. This review focuses on nanomaterials related to wearable electronics through bioinspired approaches on three different levels, interfacial packaging, sensory structure, and signal processing, which comprehensively guided recent progress of wearable devices in leveraging both nanomaterial superiorities and biorealistic functionalities. In addition, opinions on potential development trend are proposed aiming at implementing bioinspired electronics in multifunctional portable sensors, health monitoring, and intelligent prosthetics.

Memristor Circuits for Simulating Neuron Spiking and Burst Phenomena

Since the introduction of memristors, it has been widely recognized that they can be successfully employed as synapses in neuromorphic circuits. This paper focuses on showing that memristor circuits can be also used for mimicking some features of the dynamics exhibited by neurons in response to an external stimulus. The proposed approach relies on exploiting multistability of memristor circuits, i.e., the coexistence of infinitely many attractors, and employing a suitable pulse-programmed input for switching among the different attractors. Specifically, it is first shown that a circuit composed of a resistor, an inductor, a capacitor and an ideal charge-controlled memristor displays infinitely many stable equilibrium points and limit cycles, each one pertaining to a planar invariant manifold. Moreover, each limit cycle is approximated via a first-order periodic approximation analytically obtained via the Describing Function (DF) method, a well-known technique in the Harmonic Balance (HB) context. Then, it is shown that the memristor charge is capable to mimic some simplified models of the neuron response when an external independent pulse-programmed current source is introduced in the circuit. The memristor charge behavior is generated via the concatenation of convergent and oscillatory behaviors which are obtained by switching between equilibrium points and limit cycles via a properly designed pulse timing of the current source. The design procedure takes also into account some relationships between the pulse features and the circuit parameters which are derived exploiting the analytic approximation of the limit cycles obtained via the DF method.

Hybrid oxide brain-inspired neuromorphic devices for hardware implementation of artificial intelligence

The state-of-the-art artificial intelligence technologies mainly rely on deep learning algorithms based on conventional computers with classical von Neumann computing architectures, where the memory and processing units are separated resulting in an enormous amount of energy and time consumed in the data transfer process. Inspired by the human brain acting like an ultra-highly efficient biological computer, neuromorphic computing is proposed as a technology for hardware implementation of artificial intelligence. Artificial synapses are the main component of a neuromorphic computing architecture. Memristors are considered to be a relatively ideal candidate for artificial synapse applications due to their high scalability and low power consumption. Oxides are most widely used in memristors due to the ease of fabrication and high compatibility with complementary metal-oxide-semiconductor processes. However, oxide memristors suffer from unsatisfactory stability and reliability. Oxide-based hybrid structures can effectively improve the device stability and reliability, therefore providing a promising prospect for the application of oxide memristors to neuromorphic computing. This work reviews the recent advances in the development of hybrid oxide memristive synapses. The discussion is organized according to the blending schemes as well as the working mechanisms of hybrid oxide memristors.

On the Thermal Models for Resistive Random Access Memory Circuit Simulation

Resistive Random Access Memories (RRAMs) are based on resistive switching (RS) operation and exhibit a set of technological features that make them ideal candidates for applications related to non-volatile memories, neuromorphic computing and hardware cryptography. For the full industrial development of these devices different simulation tools and compact models are needed in order to allow computer-aided design, both at the device and circuit levels. Most of the different RRAM models presented so far in the literature deal with temperature effects since the physical mechanisms behind RS are thermally activated; therefore, an exhaustive description of these effects is essential. As far as we know, no revision papers on thermal models have been published yet; and that is why we deal with this issue here. Using the heat equation as the starting point, we describe the details of its numerical solution for a conventional RRAM structure and, later on, present models of different complexity to integrate thermal effects in complete compact models that account for the kinetics of the chemical reactions behind resistive switching and the current calculation. In particular, we have accounted for different conductive filament geometries, operation regimes, filament lateral heat losses, the use of several temperatures to characterize each conductive filament, among other issues. A 3D numerical solution of the heat equation within a complete RRAM simulator was also taken into account. A general memristor model is also formulated accounting for temperature as one of the state variables to describe electron device operation. In addition, to widen the view from different perspectives, we deal with a thermal model contextualized within the quantum point contact formalism. In this manner, the temperature can be accounted for the description of quantum effects in the RRAM charge transport mechanisms. Finally, the thermometry of conducting filaments and the corresponding models considering different dielectric materials are tackled in depth.

Synaptic transistors and neuromorphic systems based on carbon nano-materials

Carbon-based materials possessing a nanometer size and unique electrical properties perfectly address the two critical issues of transistors, the low power consumption and scalability, and are considered as a promising material in next-generation synaptic devices. In this review, carbon-based synaptic transistors were systematically summarized. In the carbon nanotube section, the synthesis of carbon nanotubes, purification of carbon nanotubes, the effect of architecture on the device performance and related carbon nanotube-based devices for neuromorphic computing were discussed. In the graphene section, the synthesis of graphene and its derivative, as well as graphene-based devices for neuromorphic computing, was systematically studied. Finally, the current challenges for carbon-based synaptic transistors were discussed.

Advances in Halide Perovskite Memristor from Lead-Based to Lead-Free Materials

Memristors have attracted considerable attention as one of the four basic circuit elements besides resistors, capacitors, and inductors. Especially, the nonvolatile memory devices have become a promising candidate for the new-generation information storage, due to their excellent write, read, and erase rates, in addition to the low-energy consumption, multistate storage, and high scalability. Among them, halide perovskite (HP) memristors have great potential to achieve low-cost practical information storage and computing. However, the usual lead-based HP memristors face serious problems of high toxicity and low stability. To alleviate the above issues, great effort has been devoted to develop lead-free HP memristors. Here, we have summarized and discussed the advances in HP memristors from lead-based to lead-free materials including memristive properties, stability, neural network applications, and memristive mechanism. Finally, the challenges and prospects of lead-free HP memristors have been discussed.

Transparent HfO x -based memristor with robust flexibility and synapse characteristics by interfacial control of oxygen vacancies movement

Hafnium oxides (HfO _x ) based flexible memristors were fabricated on polyethylene naphtholate (PEN) substrates to simulate a variety of bio-synapse functions. By optimizing the manufacturing conditions of electrode and active films, it is proved that the TiN/HfO _x /W/ITO/PEN bilayer device has robust flexibility and can still be modulated after 2000 times of bending. The memristor device exhibits better symmetrical and linear characteristics with excellent uniformity at lower programming power consumption (∼38 μW). In addition, the essential synaptic behaviors have further been achieved in the devices, including the transition from short-term plasticity to long-term plasticity and spike time-dependent plasticity. Through the analysis of I-V curves and XPS data, a switching mechanism based on HfO _x /W interface boundary drift is constructed. It is revealed that the redox reaction caused by W intercalation can effectively regulate the content of oxygen vacancy in HfO _x . At the same time, bias-induced interfacial reactions will regulate the movement of oxygen vacancies, which emulates bio-synapse functions and improves the electrical properties of the device.

Self-Powered Memristive Systems for Storage and Neuromorphic Computing

A neuromorphic computing chip that can imitate the human brain’s ability to process multiple types of data simultaneously could fundamentally innovate and improve the von-neumann computer architecture, which has been criticized. Memristive devices are among the best hardware units for building neuromorphic intelligence systems due to the fact that they operate at an inherent low voltage, use multi-bit storage, and are cost-effective to manufacture. However, as a passive device, the memristor cell needs external energy to operate, resulting in high power consumption and complicated circuit structure. Recently, an emerging self-powered memristive system, which mainly consists of a memristor and an electric nanogenerator, had the potential to perfectly solve the above problems. It has attracted great interest due to the advantages of its power-free operations. In this review, we give a systematic description of self-powered memristive systems from storage to neuromorphic computing. The review also proves a perspective on the application of artificial intelligence with the self-powered memristive system.

Advances in Memristor-Based Neural Networks

The rapid development of artificial intelligence (AI), big data analytics, cloud computing, and Internet of Things applications expect the emerging memristor devices and their hardware systems to solve massive data calculation with low power consumption and small chip area. This paper provides an overview of memristor device characteristics, models, synapse circuits, and neural network applications, especially for artificial neural networks and spiking neural networks. It also provides research summaries, comparisons, limitations, challenges, and future work opportunities.

Learning to Approximate Functions Using Nb-Doped SrTiO3 Memristors

Memristors have attracted interest as neuromorphic computation elements because they show promise in enabling efficient hardware implementations of artificial neurons and synapses. We performed measurements on interface-type memristors to validate their use in neuromorphic hardware. Specifically, we utilized Nb-doped SrTiO3 memristors as synapses in a simulated neural network by arranging them into differential synaptic pairs, with the weight of the connection given by the difference in normalized conductance values between the two paired memristors. This network learned to represent functions through a training process based on a novel supervised learning algorithm, during which discrete voltage pulses were applied to one of the two memristors in each pair. To simulate the fact that both the initial state of the physical memristive devices and the impact of each voltage pulse are unknown we injected noise into the simulation. Nevertheless, discrete updates based on local knowledge were shown to result in robust learning performance. Using this class of memristive devices as the synaptic weight element in a spiking neural network yields, to our knowledge, one of the first models of this kind, capable of learning to be a universal function approximator, and strongly suggests the suitability of these memristors for usage in future computing platforms.

Ti3C2-Based MXene Oxide Nanosheets for Resistive Memory and Synaptic Learning Applications

MXene, a new state-of-the-art two-dimensional (2D) nanomaterial, has attracted considerable interest from both industry and academia because of its excellent electrical, mechanical, and chemical properties. However, MXene-based device engineering has rarely been reported. In this study, we explored Ti₃C₂ MXene for digital and analog computing applications by engineering the top electrode. For this purpose, Ti₃C₂ MXene was synthesized by a simple chemical process, and its structural, compositional, and morphological properties were studied using various analytical tools. Finally, we explored its potential application in bipolar resistive switching (RS) and synaptic learning devices. In particular, the effect of the top electrode (Ag, Pt, and Al) on the RS properties of the Ti₃C₂ MXene-based memory devices was thoroughly investigated. Compared with the Ag and Pt top electrode-based devices, the Al/Ti₃C₂/Pt device exhibited better RS and operated more reliably, as determined by the evaluation of the charge-magnetic property and memory endurance and retention. Thus, we selected the Al/Ti₃C₂/Pt memristive device to mimic the potentiation and depression synaptic properties and spike-timing-dependent plasticity-based Hebbian learning rules. Furthermore, the electron transport in this device was found to occur by a filamentary RS mechanism (based on oxidized Ti₃C₂ MXene), as determined by analyzing the electrical fitting curves. The results suggest that the 2D Ti₃C₂ MXene is an excellent nanomaterial for non-volatile memory and synaptic learning applications.

Competing memristors for brain-inspired computing

The expeditious development of information technology has led to the rise of artificial intelligence (AI). However, conventional computing systems are prone to volatility, high power consumption, and even delay between the processor and memory, which is referred to as the von Neumann bottleneck, in implementing AI. To address these issues, memristor-based neuromorphic computing systems inspired by the human brain have been proposed. A memristor can store numerous values by changing its resistance and emulate artificial synapses in brain-inspired computing. Here, we introduce six types of memristors classified according to their operation mechanisms: ionic migration, phase change, spin, ferroelectricity, intercalation, and ionic gating. We review how memristor-based neuromorphic computing can learn, infer, and even create, using various artificial neural networks. Finally, the challenges and perspectives in the competing memristor technology for neuromorphic computing systems are discussed.

Roadmap on emerging hardware and technology for machine learning

Recent progress in artificial intelligence is largely attributed to the rapid development of machine learning, especially in the algorithm and neural network models. However, it is the performance of the hardware, in particular the energy efficiency of a computing system that sets the fundamental limit of the capability of machine learning. Data-centric computing requires a revolution in hardware systems, since traditional digital computers based on transistors and the von Neumann architecture were not purposely designed for neuromorphic computing. A hardware platform based on emerging devices and new architecture is the hope for future computing with dramatically improved throughput and energy efficiency. Building such a system, nevertheless, faces a number of challenges, ranging from materials selection, device optimization, circuit fabrication and system integration, to name a few. The aim of this Roadmap is to present a snapshot of emerging hardware technologies that are potentially beneficial for machine learning, providing the Nanotechnology readers with a perspective of challenges and opportunities in this burgeoning field.

Recent advances in optical and optoelectronic data storage based on luminescent nanomaterials

The substantial amount of data generated every second in the big data age creates a pressing requirement for new and advanced data storage techniques. Luminescent nanomaterials (LNMs) not only possess the same optical properties as their bulk materials but also have unique electronic and mechanical characteristics due to the strong constraints of photons and electrons at the nanoscale, enabling the development of revolutionary methods for data storage with superhigh storage capacity, ultra-long working lifetime, and ultra-low power consumption. In this review, we investigate the latest achievements in LNMs for constructing next-generation data storage systems, with a focus on optical data storage and optoelectronic data storage. We summarize the LNMs used in data storage, namely upconversion nanomaterials, long persistence luminescent nanomaterials, and downconversion nanomaterials, and their applications in optical data storage and optoelectronic data storage. We conclude by discussing the superiority of the two types of data storage and survey the prospects for the field.

Emerging Memristive Artificial Synapses and Neurons for Energy-Efficient Neuromorphic Computing

Memristors have recently attracted significant interest due to their applicability as promising building blocks of neuromorphic computing and electronic systems. The dynamic reconfiguration of memristors, which is based on the history of applied electrical stimuli, can mimic both essential analog synaptic and neuronal functionalities. These can be utilized as the node and terminal devices in an artificial neural network. Consequently, the ability to understand, control, and utilize fundamental switching principles and various types of device architectures of the memristor is necessary for achieving memristor-based neuromorphic hardware systems. Herein, a wide range of memristors and memristive-related devices for artificial synapses and neurons is highlighted. The device structures, switching principles, and the applications of essential synaptic and neuronal functionalities are sequentially presented. Moreover, recent advances in memristive artificial neural networks and their hardware implementations are introduced along with an overview of the various learning algorithms. Finally, the main challenges of the memristive synapses and neurons toward high-performance and energy-efficient neuromorphic computing are briefly discussed. This progress report aims to be an insightful guide for the research on memristors and neuromorphic-based computing.

Reliable organic memristors for neuromorphic computing by predefining a localized ion-migration path in crosslinkable polymer

In flexible neuromorphic systems for realizing artificial intelligence, organic memristors are essential building blocks as artificial synapses to perform information processing and memory. Despite much effort to implement artificial neural networks (ANNs) using organic memristors, the reliability of these devices is inherently hampered by global ion transportation and arbitrary growth of conductive filaments (CFs). As a result, the performance of ANNs is restricted. Herein, a novel concept for confining CF growth in organic memristors is demonstrated by exploiting the unique functionality of crosslinkable polymers. This can be achieved by predefining the localized ion-migration path (LIP) in crosslinkable polymers. In the proposed organic memristor, metal cations are locally transported along the LIP. Thus, CF growth is achieved only in a confined region. A flexible memristor with an LIP exhibits a vastly improved reliability and uniformity, and it is capable of operating with high mechanical and electrical endurance. Moreover, neuromorphic arrays based on the proposed memristor exhibit 96.3% learning accuracy, which is comparable to the ideal software baseline. The proposed concept of predefining the LIP in organic memristors is expected to provide novel platforms for the advance of flexible electronics and to realize a variety of practical neural networks for artificial intelligence applications.

Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network

This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (STDP) is demonstrated with a pair of hardware analog neurons connected through a (CoFeB)_x(LiNbO₃)_1-x nanocomposite memristor. Next, the learning convergence to a solution of binary clusterization task is analyzed in a wide range of memristive STDP parameters for a single-layer fully connected feedforward SNN. The memristive STDP behavior supplying convergence in this simple task is shown also to provide it in the handwritten digit recognition domain by the more complex SNN architecture with a Winner-Take-All competition between neurons. To investigate basic conditions necessary for training convergence, an original probabilistic generative model of a rate-based single-layer network with independent or competing neurons is built and thoroughly analyzed. The main result is a statement of "correlation growth-anticorrelation decay" principle which prompts near-optimal policy to configure model parameters. This principle is in line with requiring the binary clusterization convergence which can be defined as the necessary condition for optimal learning and used as the simple benchmark for tuning parameters of various neural network realizations with population-rate information coding. At last, a heuristic algorithm is described to experimentally find out the convergence conditions in a memristive SNN, including robustness to a device variability. Due to the generality of the proposed approach, it can be applied to a wide range of memristors and neurons of software- or hardware-based rate-coding single-layer SNNs when searching for local rules that ensure their unsupervised learning convergence in a pattern recognition task domain.

Realization of Biomimetic Synaptic Functions in a One-Cell Organic Resistive Switching Device Using the Diffusive Parameter of Conductive Filaments

Toward the successful development of artificial intelligence, artificial synapses based on resistive switching devices are essential ingredients to perform information processing in spiking neural networks. In neural processes, synaptic plasticity related to the history of neuron activity plays a critical role during learning. In resistive switching devices, it is barely possible to emulate both short-term plasticity and long-term plasticity due to the uncontrollable dynamics of the conductive filaments (CFs). Despite extensive effort to realize synaptic plasticity in such devices, it is still challenging to achieve reliable synaptic functions due to the overgrowth of CFs in a random fashion. Herein, we propose an organic resistive switching device with bio-realistic synaptic functions by adjusting the CF diffusive parameter. In the proposed device, complete synaptic plasticity provides the history-dependent change in the conductance. Moreover, the homeostatic feedback, which resembles the biological process, regulates CF growth in our device, which enhances the reliability of synaptic plasticity. This novel concept for realizing synaptic functions in organic resistive switching devices may provide a physical platform to advance the fundamental understanding of learning and memory mechanisms and develop a variety of neural circuits and neuromorphic systems that can be linked to artificial intelligence and next-generation computing paradigm.

Integration and Co-design of Memristive Devices and Algorithms for Artificial Intelligence

Memristive devices share remarkable similarities to biological synapses, dendrites, and neurons at both the physical mechanism level and unit functionality level, making the memristive approach to neuromorphic computing a promising technology for future artificial intelligence. However, these similarities do not directly transfer to the success of efficient computation without device and algorithm co-designs and optimizations. Contemporary deep learning algorithms demand the memristive artificial synapses to ideally possess analog weighting and linear weight-update behavior, requiring substantial device-level and circuit-level optimization. Such co-design and optimization have been the main focus of memristive neuromorphic engineering, which often abandons the “non-ideal” behaviors of memristive devices, although many of them resemble what have been observed in biological components. Novel brain-inspired algorithms are being proposed to utilize such behaviors as unique features to further enhance the efficiency and intelligence of neuromorphic computing, which calls for collaborations among electrical engineers, computing scientists, and neuroscientists.

Spike Encoding with Optic Sensory Neurons Enable a Pulse Coupled Neural Network for Ultraviolet Image Segmentation

Drawing inspiration from biology, neuromorphic systems are of great interest in direct interaction and efficient processing of analogue signals in the real world and could be promising for the development of smart sensors. Here, we demonstrate an artificial sensory neuron consisting of an InGaZnO₄ (IGZO₄)-based optical sensor and NbO_x-based oscillation neuron in series, which can simultaneously sense the optical information even beyond the visible light region and encode them into electrical impulses. Such artificial vision sensory neurons can convey visual information in a parallel manner analogous to biological vision systems, and the output spikes can be effectively processed by a pulse coupled neural network, demonstrating the capability of image segmentation out of a complex background. This study could facilitate the construction of artificial visual systems and pave the way for the development of light-driven neurorobotics, bioinspired optoelectronics, and neuromorphic computing.

Reinforcement learning in synthetic gene circuits

Synthetic gene circuits allow programming in DNA the expression of a phenotype at a given environmental condition. The recent integration of memory systems with gene circuits opens the door to their adaptation to new conditions and their re-programming. This lays the foundation to emulate neuromorphic behaviour and solve complex problems similarly to artificial neural networks. Cellular products such as DNA or proteins can be used to store memory in both digital and analog formats, allowing cells to be turned into living computing devices able to record information regarding their previous states. In particular, synthetic gene circuits with memory can be engineered into living systems to allow their adaptation through reinforcement learning. The development of gene circuits able to adapt through reinforcement learning moves Sciences towards the ambitious goal: the bottom-up creation of a fully fledged living artificial intelligence.

Anisotropic Signal Processing with Trigonal Selenium Nanosheet Synaptic Transistors

Hardware implementation of an artificial neural network requires neuromorphic devices to process information with low energy consumption and high heterogeneity. Here we demonstrate an electrolyte-gated synaptic transistor (EGT) based on a trigonal selenium (t-Se) nanosheet. Due to the intrinsic low conductivity of the Se channel, the t-Se synaptic transistor exhibits ultralow energy consumption, less than 0.1 pJ per spike. More importantly, the intrinsic low symmetry of t-Se offers a strong anisotropy along its c- and a-axis in electrical conductance with a ratio of up to 8.6. The multiterminal EGT device exhibits an anisotropic response of filtering behavior to the same external stimulus, which enables it to mimic the heterogeneous signal transmission process of the axon-multisynapse biostructure in the human brain. The proof-of-concept device in this work represents an important step to develop neuromorphic electronics for processing complex signals.

Neural signal analysis with memristor arrays towards high-efficiency brain-machine interfaces

Brain-machine interfaces are promising tools to restore lost motor functions and probe brain functional mechanisms. As the number of recording electrodes has been exponentially rising, the signal processing capability of brain–machine interfaces is falling behind. One of the key bottlenecks is that they adopt conventional von Neumann architecture with digital computation that is fundamentally different from the working principle of human brain. In this work, we present a memristor-based neural signal analysis system, where the bio-plausible characteristics of memristors are utilized to analyze signals in the analog domain with high efficiency. As a proof-of-concept demonstration, memristor arrays are used to implement the filtering and identification of epilepsy-related neural signals, achieving a high accuracy of 93.46%. Remarkably, our memristor-based system shows nearly 400× improvements in the power efficiency compared to state-of-the-art complementary metal-oxide-semiconductor systems. This work demonstrates the feasibility of using memristors for high-performance neural signal analysis in next-generation brain–machine interfaces.

Designing energy efficient and high performance brain-machine interfaces with millions of recording electrodes for in-situ analysis remains a challenge. Here, the authors develop a memristor-based neural signal analysis system capable of filtering and identifying epilepsy-related brain activities with an accuracy of 93.46%.

In-Memory Logic Operations and Neuromorphic Computing in Non-Volatile Random Access Memory

Recent progress in the development of artificial intelligence technologies, aided by deep learning algorithms, has led to an unprecedented revolution in neuromorphic circuits, bringing us ever closer to brain-like computers. However, the vast majority of advanced algorithms still have to run on conventional computers. Thus, their capacities are limited by what is known as the von-Neumann bottleneck, where the central processing unit for data computation and the main memory for data storage are separated. Emerging forms of non-volatile random access memory, such as ferroelectric random access memory, phase-change random access memory, magnetic random access memory, and resistive random access memory, are widely considered to offer the best prospect of circumventing the von-Neumann bottleneck. This is due to their ability to merge storage and computational operations, such as Boolean logic. This paper reviews the most common kinds of non-volatile random access memory and their physical principles, together with their relative pros and cons when compared with conventional CMOS-based circuits (Complementary Metal Oxide Semiconductor). Their potential application to Boolean logic computation is then considered in terms of their working mechanism, circuit design and performance metrics. The paper concludes by envisaging the prospects offered by non-volatile devices for future brain-inspired and neuromorphic computation.

The coexistence of threshold and memory switching characteristics of ALD HfO2 memristor synaptic arrays for energy-efficient neuromorphic computing

The development of bioinspired electronic devices that can mimic the biological synapses is an essential step towards the development of efficient neuromorphic systems to simulate the functions of the human brain. Among various materials that can be utilized to attain electronic synapses, the existing semiconductor industry-compatible conventional materials are more favorable due to their low cost, easy fabrication and reliable switching properties. In this work, atomic layer deposited HfO2-based memristor synaptic arrays are fabricated. The coexistence of threshold switching (TS) and memory switching (MS) behaviors is obtained by modulating the device current. The TS characteristics are exploited to emulate essential synaptic functions. The Ag diffusive dynamics of our electronic synapses, analogous to the Ca2+ dynamics in biological synapses, is utilized to emulate synaptic functions. Electronic synapses successfully emulate paired-pulse facilitation (PPF), post-tetanic potentiation (PTP), spike-timing-dependent plasticity (STDP), short-term potentiation (STP), long-term potentiation (LTP) and transition from STP to LTP with rehearsals. The psychological memorization model of short-term memory (STM) to long-term memory (LTM) transition is mimicked by image memorization in crossbar array devices. Reliable and repeatable bipolar MS behaviors with a low operating voltage are obtained by a higher compliance current for energy-efficient nonvolatile memory applications.

Neuromorphic nanoelectronic materials

Memristive and nanoionic devices have recently emerged as leading candidates for neuromorphic computing architectures. While top-down fabrication based on conventional bulk materials has enabled many early neuromorphic devices and circuits, bottom-up approaches based on low-dimensional nanomaterials have shown novel device functionality that often better mimics a biological neuron. In addition, the chemical, structural and compositional tunability of low-dimensional nanomaterials coupled with the permutational flexibility enabled by van der Waals heterostructures offers significant opportunities for artificial neural networks. In this Review, we present a critical survey of emerging neuromorphic devices and architectures enabled by quantum dots, metal nanoparticles, polymers, nanotubes, nanowires, two-dimensional layered materials and van der Waals heterojunctions with a particular emphasis on bio-inspired device responses that are uniquely enabled by low-dimensional topology, quantum confinement and interfaces. We also provide a forward-looking perspective on the opportunities and challenges of neuromorphic nanoelectronic materials in comparison with more mature technologies based on traditional bulk electronic materials.

Evidence of Biorealistic Synaptic Behavior in Diffusive Li-based Two-terminal Resistive Switching Devices

Following the recent advances in artificial synaptic devices and the renewed interest regarding artificial intelligence and neuromorphic computing, a new two-terminal resistive switching device, based on mobile Li⁺ ions is hereby explored. Emulation of neural functionalities in a biorealistic manner has been recently implemented through the use of synaptic devices with diffusive dynamics. Mimicking of the spontaneous synaptic weight relaxation of neuron cells, which is regulated by the concentration kinetics of positively charged ions like Ca²⁺, is facilitated through the conductance relaxation of such diffusive devices. Adopting a battery-like architecture, using LiCoO₂ as a resistive switching cathode layer, SiO_x as an electrolyte and TiO₂ as an anode, Au/LiCoO₂/SiO_x/TiO₂/p⁺⁺-Si two-terminal devices have been fabricated. Analog conductance modulation, via voltage-driven regulation of Li⁺ ion concentration in the cathode and anode layers, along with current rectification and nanobattery effects are reported. Furthermore, evidence is provided for biorealistic synaptic behavior, manifested as paired pulse facilitation based on the summation of excitatory post-synaptic currents and spike-timing-dependent plasticity, which are governed by the Li⁺ ion concentration and its relaxation dynamics.

Hydrothermally Grown TiO2 Nanorod Array Memristors with Volatile States

In the present study, the memristive characteristics of hydrothermally grown TiO₂ nanorod arrays, particularly, the difference in the retention time of the resistance state, are investigated in dependence of the array growth temperature. A volatile behavior is observed and related to a redistribution of oxygen vacancies over time. It is shown that the retention time increases for increasing array growth temperatures from several seconds up to 20 min. The relaxation behavior is also seen in the current-voltage characteristics, which do not show the common unipolar, bipolar, or complementary switching behavior. Instead, the temporal evolution depends on the duration of the applied voltage and on the nanowire growth temperature. Therefore, electronic measurements are combined with scanning electron and scanning transmission electron microscopy, so that the amount of oxygen defect-rich grain boundaries in the upper part of the nanowires can be linked to the differences in the current-voltage behavior and retention time.

Piezotronic Synapse Based on a Single GaN Microwire for Artificial Sensory Systems

Tactile information is efficiently captured and processed through a complex sensory system combined with mechanoreceptors, neurons, and synapses in human skin. Synapses are essential for tactile signal transmission between pre/post-neurons. However, developing an electronic device that integrates the functions of tactile information sensation and transmission remains a challenge. Here, we present a piezotronic synapse based on a single GaN microwire that can simultaneously achieve the capabilities of strain sensing and synaptic functions. The piezotronic effect in the wurtzite GaN is introduced to strengthen synaptic weight updates (e.g., 330% enhancement at a compressive stress of -0.36%) with pulse trains. A high gauge factor for strain sensing (ranging from 0 to -0.81%) of about 736 is also obtained. Remarkably, the piezotronic synapse enables the neuromorphic hardware achievement of the perception and processing of tactile information in a single micro/nanowire system, demonstrating an advance in biorealistic artificial intelligence systems.

Neurohybrid Memristive CMOS-Integrated Systems for Biosensors and Neuroprosthetics

Here we provide a perspective concept of neurohybrid memristive chip based on the combination of living neural networks cultivated in microfluidic/microelectrode system, metal-oxide memristive devices or arrays integrated with mixed-signal CMOS layer to control the analog memristive circuits, process the decoded information, and arrange a feedback stimulation of biological culture as parts of a bidirectional neurointerface. Our main focus is on the state-of-the-art approaches for cultivation and spatial ordering of the network of dissociated hippocampal neuron cells, fabrication of a large-scale cross-bar array of memristive devices tailored using device engineering, resistive state programming, or non-linear dynamics, as well as hardware implementation of spiking neural networks (SNNs) based on the arrays of memristive devices and integrated CMOS electronics. The concept represents an example of a brain-on-chip system belonging to a more general class of memristive neurohybrid systems for a new-generation robotics, artificial intelligence, and personalized medicine, discussed in the framework of the proposed roadmap for the next decade period.

Bioinspired bio-voltage memristors

Memristive devices are promising candidates to emulate biological computing. However, the typical switching voltages (0.2-2 V) in previously described devices are much higher than the amplitude in biological counterparts. Here we demonstrate a type of diffusive memristor, fabricated from the protein nanowires harvested from the bacterium Geobacter sulfurreducens, that functions at the biological voltages of 40-100 mV. Memristive function at biological voltages is possible because the protein nanowires catalyze metallization. Artificial neurons built from these memristors not only function at biological action potentials (e.g., 100 mV, 1 ms) but also exhibit temporal integration close to that in biological neurons. The potential of using the memristor to directly process biosensing signals is also demonstrated.

Designing energy efficient systems capable to directly process signals at biological voltages remains a challenge. Here, the authors propose a bio-compatible memristor device based on protein-nanowire dielectric, harvested from the bacterium Geobactor sulfurreducens, working at biological voltages.

Further results on finite-time synchronization of delayed inertial memristive neural networks via a novel analysis method

In this paper, we propose a novel analysis method to investigate the finite-time synchronization (FTS) control problem of the drive-response inertial memristive neural networks (IMNNs) with mixed time-varying delays (MTVDs). Firstly, an improved control scheme is proposed under the delay-independent conditions, which can work even when the past state cannot be measured or the specific time delay function is unknown. Secondly, based on the assumption of bounded activation functions, we establish a new Lemma, which can effectively deal with the difficulties caused by memristive connection weights and MTVDs. Thirdly, by constructing a suitable Lyapunov functions and using a new inequality method, novel sufficient conditions to ensure the FTS for the discussed IMNNs are obtained. Compared with the existing results, our results obtained in a more general framework are more practical. Finally, some numerical simulations are given to substantiate the effectiveness of the theoretical results.

Excellent synaptic behavior of lithium-based nano-ionic transistor based on optimal WO2.7 stoichiometry with high ion diffusivity

In this study, we introduce a lithium (Li) ion-based three-terminal (3-T) synapse device using WO _x as a channel. Our study reveals a key stoichiometry of WO_2.7 for excellent synaptic characteristics that is related to Li-ion diffusivity. The open-lattice structure formed by oxygen deficiency promoted Li-ion injection and diffusion. The optimized stoichiometry and improved Li-ion diffusivity were confirmed by x-ray photoelectron spectroscopy analysis and cyclic voltammetry, respectively. Furthermore, the transient conductance change that inevitably occurs in ion-based synaptic transistors was resolved by applying a two-step voltage pulse scheme. As a result, we achieved a symmetric and linear weight-update characteristic with reduced program/erase operation time.

Toward a generalized Bienenstock-Cooper-Munro rule for spatiotemporal learning via triplet-STDP in memristive devices

The close replication of synaptic functions is an important objective for achieving a highly realistic memristor-based cognitive computation. The emulation of neurobiological learning rules may allow the development of neuromorphic systems that continuously learn without supervision. In this work, the Bienenstock-Cooper-Munro learning rule, as a typical case of spike-rate-dependent plasticity, is mimicked using a generalized triplet-spike-timing-dependent plasticity scheme in a WO_3-x memristive synapse. It demonstrates both presynaptic and postsynaptic activities and remedies the absence of the enhanced depression effect in the depression region, allowing a better description of the biological counterpart. The threshold sliding effect of Bienenstock-Cooper-Munro rule is realized using a history-dependent property of the second-order memristor. Rate-based orientation selectivity is demonstrated in a simulated feedforward memristive network with this generalized Bienenstock-Cooper-Munro framework. These findings provide a feasible approach for mimicking Bienenstock-Cooper-Munro learning rules in memristors, and support the applications of spatiotemporal coding and learning using memristive networks.

Electroforming in Metal-Oxide Memristive Synapses

Memristors have shown an extraordinary potential to emulate the plastic and dynamic electrical behaviors of biological synapses and have been already used to construct neuromorphic systems with in-memory computing and unsupervised learning capabilities; moreover, the small size and simple fabrication process of memristors make them ideal candidates for ultradense configurations. So far, the properties of memristive electronic synapses (i.e., potentiation/depression, relaxation, linearity) have been extensively analyzed by several groups. However, the dynamics of electroforming in memristive devices, which defines the position, size, shape, and chemical composition of the conductive nanofilaments across the device, has not been analyzed in depth. By applying ramped voltage stress (RVS), constant voltage stress (CVS), and pulsed voltage stress (PVS), we found that electroforming is highly affected by the biasing methods applied. We also found that the technique used to deposit the oxide, the chemical composition of the adjacent metal electrodes, and the polarity of the electrical stimuli applied have important effects on the dynamics of the electroforming process and in subsequent post-electroforming bipolar resistive switching. This work should be of interest to designers of memristive neuromorphic systems and could open the door for the implementation of new bioinspired functionalities into memristive neuromorphic systems.

Spatial Properties of STDP in a Self-Learning Spiking Neural Network Enable Controlling a Mobile Robot

Development of spiking neural networks (SNNs) controlling mobile robots is one of the modern challenges in computational neuroscience and artificial intelligence. Such networks, being replicas of biological ones, are expected to have a higher computational potential than traditional artificial neural networks (ANNs). The critical problem is in the design of robust learning algorithms aimed at building a “living computer” based on SNNs. Here, we propose a simple SNN equipped with a Hebbian rule in the form of spike-timing-dependent plasticity (STDP). The SNN implements associative learning by exploiting the spatial properties of STDP. We show that a LEGO robot controlled by the SNN can exhibit classical and operant conditioning. Competition of spike-conducting pathways in the SNN plays a fundamental role in establishing associations of neural connections. It replaces the irrelevant associations by new ones in response to a change in stimuli. Thus, the robot gets the ability to relearn when the environment changes. The proposed SNN and the stimulation protocol can be further enhanced and tested in developing neuronal cultures, and also admit the use of memristive devices for hardware implementation.

Emerging neuromorphic devices

Artificial intelligence (AI) has the ability of revolutionizing our lives and society in a radical way, by enabling machine learning in the industry, business, health, transportation, and many other fields. The ability to recognize objects, faces, and speech, requires, however, exceptional computational power and time, which is conflicting with the current difficulties in transistor scaling due to physical and architectural limitations. As a result, to accelerate the progress of AI, it is necessary to develop materials, devices, and systems that closely mimic the human brain. In this work, we review the current status and challenges on the emerging neuromorphic devices for brain-inspired computing. First, we provide an overview of the memory device technologies which have been proposed for synapse and neuron circuits in neuromorphic systems. Then, we describe the implementation of synaptic learning in the two main types of neural networks, namely the deep neural network and the spiking neural network (SNN). Bio-inspired learning, such as the spike-timing dependent plasticity scheme, is shown to enable unsupervised learning processes which are typical of the human brain. Hardware implementations of SNNs for the recognition of spatial and spatio-temporal patterns are also shown to support the cognitive computation in silico. Finally, we explore the recent advances in reproducing bio-neural processes via device physics, such as insulating-metal transitions, nanoionics drift/diffusion, and magnetization flipping in spintronic devices. By harnessing the device physics in emerging materials, neuromorphic engineering with advanced functionality, higher density and better energy efficiency can be developed.

Stabilization of Second-Order Memristive Neural Networks With Mixed Time Delays via Nonreduced Order

In this brief, we investigate a class of second-order memristive neural networks (SMNNs) with mixed time-varying delays. Based on nonsmooth analysis, the Lyapunov stability theory, and adaptive control theory, several new results ensuring global stabilization of the SMNNs are obtained. In addition, compared with the reduced-order method used in the existing research studies, we consider the global stabilization directly from the SMNNs themselves without the reduced-order method. Finally, we give some numerical simulations to show the effectiveness of the results.

Improvement of Conductance Modulation Linearity in a Cu2+-Doped KNbO3 Memristor through the Increase of the Number of Oxygen Vacancies

The Pt/KNbO₃/TiN/Si (KN) memristor exhibits various biological synaptic properties. However, it also displays nonlinear conductance modulation with the application of identical pulses, indicating that it should be improved for neuromorphic applications. The abrupt change of the conductance originates from the inhomogeneous growth/dissolution of oxygen vacancy filaments in the KN film. The change of the filaments in a KN film is controlled by two mechanisms with different growth/dissolution rates: a redox process with a fast rate and an oxygen vacancy diffusion process with a slow rate. Therefore, the conductance modulation linearity can be improved if the growth/dissolution of the filaments is controlled by only one mechanism. When the number of oxygen vacancies in the KN film was increased through doping of Cu²⁺ ions, the growth/dissolution of the filaments in the Cu²⁺-doped KN (CKN) film was mainly influenced by the redox process of oxygen vacancies. Therefore, the CKN film exhibited improved conductance modulation linearity, confirming that the linearity of conductance modulation can be improved by increasing the number of oxygen vacancies in the memristor. This method can be applied to other memristors to improve the linearity of conductance modulation. The CKN memristor also provides excellent biological synaptic characteristics for neuromorphic computing systems.

Memristive and CMOS Devices for Neuromorphic Computing

Neuromorphic computing has emerged as one of the most promising paradigms to overcome the limitations of von Neumann architecture of conventional digital processors. The aim of neuromorphic computing is to faithfully reproduce the computing processes in the human brain, thus paralleling its outstanding energy efficiency and compactness. Toward this goal, however, some major challenges have to be faced. Since the brain processes information by high-density neural networks with ultra-low power consumption, novel device concepts combining high scalability, low-power operation, and advanced computing functionality must be developed. This work provides an overview of the most promising device concepts in neuromorphic computing including complementary metal-oxide semiconductor (CMOS) and memristive technologies. First, the physics and operation of CMOS-based floating-gate memory devices in artificial neural networks will be addressed. Then, several memristive concepts will be reviewed and discussed for applications in deep neural network and spiking neural network architectures. Finally, the main technology challenges and perspectives of neuromorphic computing will be discussed.

Defect-Engineered Electroforming-Free Analog HfOx Memristor and Its Application to the Neural Network

The thin-film growth conditions in a plasma-enhanced atomic layer deposition for the (3.0-4.5) nm thick HfO₂ film were optimized to use the film as the resistive switching element in a neuromorphic circuit. The film was intended to be used as a feasible synapse with analog-type conductance-tuning capability. The 4.5 nm thick HfO₂ films on both conventional TiN and a new RuO₂ bottom electrode required the electroforming process for them to operate as a feasible resistive switching memory, which was the primary source of the undesirable characteristics as the synapse. Therefore, electroforming-free performance was necessary, which could be accomplished by thinning the HfO₂ film down to 3.0 nm. However, the device with only the RuO₂ bottom electrode offered the desired functionality without involving too high leakage or shorting problems, which are due to the recovery of the stoichiometric composition of the HfO₂ near the RuO₂ layer. In conjunction with the Ta top electrode, which provided the necessary oxygen vacancies to the HfO₂ layer, and the high functionality of the RuO₂ as the scavenger of excessive incorporated oxygen vacancies, which appeared to be inevitable during the repeated switching operation, the Ta/3.0 nm HfO₂/RuO₂ provided a highly useful synaptic device component in the neuromorphic hardware system.

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

As the research on artificial intelligence booms, there is broad interest in brain-inspired computing using novel neuromorphic devices. The potential of various emerging materials and devices for neuromorphic computing has attracted extensive research efforts, leading to a large number of publications. Going forward, in order to better emulate the brain's functions, its relevant fundamentals, working mechanisms, and resultant behaviors need to be re-visited, better understood, and connected to electronics. A systematic overview of biological and artificial neural systems is given, along with their related critical mechanisms. Recent progress in neuromorphic devices is reviewed and, more importantly, the existing challenges are highlighted to hopefully shed light on future research directions.

Decoding the metallic bridging dynamics in nanogap atomic switches

Atomic switches are promising candidates as the basic building blocks for large-scale neuromorphic networks due to their tunable switching behaviors. Several neuromorphic components based on atomic switches have been demonstrated, including artificial synapses, artificial neurons and short-term to long-term memory, making it possible to construct neuromorphic systems using a unified device. Although the mechanism of atomic switches has been actively studied, most of the discussions in previous studies are qualitative and failed to provide a comprehensive view of the dynamics that can precisely describe the metallic bridging under an electric field. In this paper, we designed a gap-type atomic switch and realized various switching behaviors, including both volatile and non-volatile resistive switching. Employing advanced microanalysis technology, we experimentally studied the switching mechanism and captured the nanoscale metallic filament in gap-type atomic switches. Furthermore, based on the experimental findings as well as on the electrochemistry fundamental and electron tunneling effect, we proposed a physical model that precisely reproduced the sophisticated switching behaviors. Our model mathematically described the growth/shrinkage dynamics of nanoscale metallic filaments, providing a direction for studying the switching behaviors from a quantitative view. The simulation results are in good agreement with the experimental findings in both DC sweep and pulse operation modes. In addition, we have demonstrated neuronal tonic spiking and short-term to long-term memory in experiment and simulation, indicating that our model can be applied to the circuit level simulation of large-scale atomic switch arrays for neuromorphic applications.

Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network

Brain-inspired neuromorphic systems (hardware neural networks) are expected to be an energy-efficient computing architecture for solving cognitive tasks, which critically depend on the development of reliable synaptic weight storage (i.e., synaptic device). Although various nanoelectronic devices have successfully reproduced the learning rules of biological synapses through their internal analog conductance states, the sustainability of such devices is still in doubt due to the variability common to all nanoelectronic devices. Alternatively, a neuromorphic system based on a relatively more reliable digital-type switching device has been recently demonstrated, i.e., a binarized neural network (BNN). The synaptic device is a more mature digital-type switching device, and the training/recognition algorithm developed for the BNN enables the task of facial image classification with a supervised training scheme. Here, we quantitatively investigate the effects of device parameter variations on the classification accuracy; the parameters include the number of weight states (N_state), the weight update margin (ΔG), and the weight update variation (G_var). This analysis demonstrates the feasibility of the BNN and introduces a practical neuromorphic system based on mature, conventional digital device technologies.