Hybrid 2D-CMOS microchips for memristive applications.

Exploiting the excellent electronic properties of two-dimensional (2D) materials to fabricate advanced electronic circuits is a major goal for the semiconductor industry1,2. However, most studies in this field have been limited to the fabrication and characterization of isolated large (more than 1 µm2) devices on unfunctional SiO2-Si substrates. Some studies have integrated monolayer graphene on silicon microchips as a large-area (more than 500 µm2) interconnection3 and as a channel of large transistors (roughly 16.5 µm2) (refs. 4,5), but in all cases the integration density was low, no computation was demonstrated and manipulating monolayer 2D materials was challenging because native pinholes and cracks during transfer increase variability and reduce yield. Here, we present the fabrication of high-integration-density 2D-CMOS hybrid microchips for memristive applications-CMOS stands for complementary metal-oxide-semiconductor. We transfer a sheet of multilayer hexagonal boron nitride onto the back-end-of-line interconnections of silicon microchips containing CMOS transistors of the 180 nm node, and finalize the circuits by patterning the top electrodes and interconnections. The CMOS transistors provide outstanding control over the currents across the hexagonal boron nitride memristors, which allows us to achieve endurances of roughly 5 million cycles in memristors as small as 0.053 µm2. We demonstrate in-memory computation by constructing logic gates, and measure spike-timing dependent plasticity signals that are suitable for the implementation of spiking neural networks. The high performance and the relatively-high technology readiness level achieved represent a notable advance towards the integration of 2D materials in microelectronic products and memristive applications.

In materia reservoir computing with a fully memristive architecture based on self-organizing nanowire networks.

Neuromorphic computing aims at the realization of intelligent systems able to process information similarly to our brain. Brain-inspired computing paradigms have been implemented in crossbar arrays of memristive devices; however, this approach does not emulate the topology and the emergent behaviour of biological neuronal circuits, where the principle of self-organization regulates both structure and function. Here, we report on in materia reservoir computing in a fully memristive architecture based on self-organized nanowire networks. Thanks to the functional synaptic connectivity with nonlinear dynamics and fading memory properties, the designless nanowire complex network acts as a network-wide physical reservoir able to map spatio-temporal inputs into a feature space that can be analysed by a memristive resistive switching memory read-out layer. Computing capabilities, including recognition of spatio-temporal patterns and time-series prediction, show that the emergent memristive behaviour of nanowire networks allows in materia implementation of brain-inspired computing paradigms characterized by a reduced training cost.

Three-Terminal Ovonic Threshold Switch (3T-OTS) with Tunable Threshold Voltage for Versatile Artificial Sensory Neurons.

Inspired by information processing in biological systems, sensor-combined edge-computing systems attract attention requesting artificial sensory neurons as essential ingredients. Here, we introduce a simple and versatile structure of artificial sensory neurons based on a novel three-terminal Ovonic threshold switch (3T-OTS), which features an electrically controllable threshold voltage (Vth). Combined with a sensor driving an output voltage, this 3T-OTS generates spikes with a frequency depending on an external stimulus. As a proof of concept, we have built an artificial retinal ganglion cell (RGC) by combining a 3T-OTS and a photodiode. Furthermore, this artificial RGC is combined with the reservoir-computing technique to perform a classification of chest X-ray images for normal, viral pneumonia, and COVID-19 infections, releasing the recognition accuracy of about 86.5%. These results indicate that the 3T-OTS is highly promising for applications in neuromorphic sensory systems, providing a building block for energy-efficient in-sensor computing devices.

A CMOS-memristor hybrid system for implementing stochastic binary spike timing-dependent plasticity.

This paper describes a fully experimental hybrid system in which a [Formula: see text] memristive crossbar spiking neural network (SNN) was assembled using custom high-resistance state memristors with analogue CMOS neurons fabricated in 180 nm CMOS technology. The custom memristors used NMOS selector transistors, made available on a second 180 nm CMOS chip. One drawback is that memristors operate with currents in the micro-amperes range, while analogue CMOS neurons may need to operate with currents in the pico-amperes range. One possible solution was to use a compact circuit to scale the memristor-domain currents down to the analogue CMOS neuron domain currents by at least 5-6 orders of magnitude. Here, we proposed using an on-chip compact current splitter circuit based on MOS ladders to aggressively attenuate the currents by over 5 orders of magnitude. This circuit was added before each neuron. This paper describes the proper experimental operation of an SNN circuit using a [Formula: see text] 1T1R synaptic crossbar together with four post-synaptic CMOS circuits, each with a 5-decade current attenuator and an integrate-and-fire neuron. It also demonstrates one-shot winner-takes-all training and stochastic binary spike-timing-dependent-plasticity learning using this small system. This article is part of the theme issue 'Advanced neurotechnologies: translating innovation for health and well-being'.

Solving matrix equations in one step with cross-point resistive arrays.

Conventional digital computers can execute advanced operations by a sequence of elementary Boolean functions of 2 or more bits. As a result, complicated tasks such as solving a linear system or solving a differential equation require a large number of computing steps and an extensive use of memory units to store individual bits. To accelerate the execution of such advanced tasks, in-memory computing with resistive memories provides a promising avenue, thanks to analog data storage and physical computation in the memory. Here, we show that a cross-point array of resistive memory devices can directly solve a system of linear equations, or find the matrix eigenvectors. These operations are completed in just one single step, thanks to the physical computing with Ohm's and Kirchhoff's laws, and thanks to the negative feedback connection in the cross-point circuit. Algebraic problems are demonstrated in hardware and applied to classical computing tasks, such as ranking webpages and solving the Schrödinger equation in one step.

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.

Impact of oxide and electrode materials on the switching characteristics of oxide ReRAM devices.

Resistive switching random-access memory (ReRAM) is one of the most promising technologies for non-volatile memories. Thanks to the low power and high speed operation, the high density CMOS-compatible integration, and the high cycling endurance, the ReRAM technology is becoming a strong candidate for high-density storage arrays and novel in-memory computing systems. However, ReRAM suffers from cycle-to-cycle switching variability and noise-induced resistance fluctuations, leading to insufficient read margin between the programmed resistive states. To overcome the existing challenges, a deep understanding of the roles of the ReRAM materials in the device characteristics is essential. To better understand the role of the switching layer material in controlling ReRAM performance and reliability, this work compares SiOx- and HfO2-based ReRAM at fixed geometry and electrode materials. Ti/HfO2/C and Ti/SiOx/C devices are compared from the point of view of the forming process, switching characteristics, resistance variability, and temperature stability of the programmed states. The results show clear similarities for the two different oxides, including a similar resistance window and stability at high temperatures, thus suggesting a common nature of the switching mechanism, highlighting the importance of the electrodes. On the other hand, the oxide materials play a clear role in the forming, breakdown, and variability characteristics. The discrimination between the role of the oxide and the electrode materials in the ReRAM allows ReRAM optimization via materials engineering to be better explored for future memory and computing applications.

Self-aligned nanotube-nanowire phase change memory.

A central issue of nanoelectronics concerns their fundamental scaling limits, that is, the smallest and most energy-efficient devices that can function reliably. Unlike charge-based electronics that are prone to leakage at nanoscale dimensions, memory devices based on phase change materials (PCMs) are more scalable, storing digital information as the crystalline or amorphous state of a material. Here, we describe a novel approach to self-align PCM nanowires with individual carbon nanotube (CNT) electrodes for the first time. The highly scaled and spatially confined memory devices approach the ultimate scaling limits of PCM technology, achieving ultralow programming currents (~0.1 µA set, ~1.6 µA reset), outstanding on/off ratios (~10(3)), and improved endurance and stability at few-nanometer bit dimensions. In addition, the powerful yet simple nanofabrication approach described here can enable confining and probing many other nanoscale and molecular devices self-aligned with CNT electrodes.

Memristive tonotopic mapping with volatile resistive switching memory devices.

To reach the energy efficiency and the computing capability of biological neural networks, novel hardware systems and paradigms are required where the information needs to be processed in both spatial and temporal domains. Resistive switching memory (RRAM) devices appear as key enablers for the implementation of large-scale neuromorphic computing systems with high energy efficiency and extended scalability. Demonstrating a full set of spatiotemporal primitives with RRAM-based circuits remains an open challenge. By taking inspiration from the neurobiological processes in the human auditory systems, we develop neuromorphic circuits for memristive tonotopic mapping via volatile RRAM devices. Based on a generalized stochastic device-level approach, we demonstrate the main features of signal processing of cochlea, namely logarithmic integration and tonotopic mapping of signals. We also show that our tonotopic classification is suitable for speech recognition. These results support memristive devices for physical processing of temporal signals, thus paving the way for energy efficient, high density neuromorphic systems.

Hemispherical Retina Emulated by Plasmonic Optoelectronic Memristors with All-Optical Modulation for Neuromorphic Stereo Vision.

Binocular stereo vision relies on imaging disparity between two hemispherical retinas, which is essential to acquire image information in three dimensional environment. Therefore, retinomorphic electronics with structural and functional similarities to biological eyes are always highly desired to develop stereo vision perception system. In this work, a hemispherical optoelectronic memristor array based on Ag-TiO2 nanoclusters/sodium alginate film is developed to realize binocular stereo vision. All-optical modulation induced by plasmonic thermal effect and optical excitation in Ag-TiO2 nanoclusters is exploited to realize in-pixel image sensing and storage. Wide field of view (FOV) and spatial angle detection are experimentally demonstrated owing to the device arrangement and incident-angle-dependent characteristics in hemispherical geometry. Furthermore, depth perception and motion detection based on binocular disparity have been realized by constructing two retinomorphic memristive arrays. The results demonstrated in this work provide a promising strategy to develop all-optically controlled memristor and promote the future development of binocular vision system with in-sensor architecture.

Hardware implementation of memristor-based artificial neural networks.

Artificial Intelligence (AI) is currently experiencing a bloom driven by deep learning (DL) techniques, which rely on networks of connected simple computing units operating in parallel. The low communication bandwidth between memory and processing units in conventional von Neumann machines does not support the requirements of emerging applications that rely extensively on large sets of data. More recent computing paradigms, such as high parallelization and near-memory computing, help alleviate the data communication bottleneck to some extent, but paradigm- shifting concepts are required. Memristors, a novel beyond-complementary metal-oxide-semiconductor (CMOS) technology, are a promising choice for memory devices due to their unique intrinsic device-level properties, enabling both storing and computing with a small, massively-parallel footprint at low power. Theoretically, this directly translates to a major boost in energy efficiency and computational throughput, but various practical challenges remain. In this work we review the latest efforts for achieving hardware-based memristive artificial neural networks (ANNs), describing with detail the working principia of each block and the different design alternatives with their own advantages and disadvantages, as well as the tools required for accurate estimation of performance metrics. Ultimately, we aim to provide a comprehensive protocol of the materials and methods involved in memristive neural networks to those aiming to start working in this field and the experts looking for a holistic approach.

Reservoir Computing with Charge-Trap Memory Based on a MoS2 Channel for Neuromorphic Engineering.

Novel memory devices are essential for developing low power, fast, and accurate in-memory computing and neuromorphic engineering concepts that can compete with the conventional complementary metal-oxide-semiconductor (CMOS) digital processors. 2D semiconductors provide a novel platform for advanced semiconductors with atomic thickness, low-current operation, and capability of 3D integration. This work presents a charge-trap memory (CTM) device with a MoS2 channel where memory operation arises, thanks to electron trapping/detrapping at interface states. Transistor operation, memory characteristics, and synaptic potentiation/depression for neuromorphic applications are demonstrated. The CTM device shows outstanding linearity of the potentiation by applied drain pulses of equal amplitude. Finally, pattern recognition is demonstrated by reservoir computing where the input pattern is applied as a stimulation of the MoS2 -based CTMs, while the output current after stimulation is processed by a feedforward readout network. The good accuracy, the low current operation, and the robustness to input random bit flip makes the CTM device a promising technology for future high-density neuromorphic computing concepts.

Ionic-electronic halide perovskite memdiodes enabling neuromorphic computing with a second-order complexity.

With increasing computing demands, serial processing in von Neumann architectures built with zeroth-order complexity digital circuits is saturating in computational capacity and power, entailing research into alternative paradigms. Brain-inspired systems built with memristors are attractive owing to their large parallelism, low energy consumption, and high error tolerance. However, most demonstrations have thus far only mimicked primitive lower-order biological complexities using devices with first-order dynamics. Memristors with higher-order complexities are predicted to solve problems that would otherwise require increasingly elaborate circuits, but no generic design rules exist. Here, we present second-order dynamics in halide perovskite memristive diodes (memdiodes) that enable Bienenstock-Cooper-Munro learning rules capturing both timing- and rate-based plasticity. A triplet spike timing-dependent plasticity scheme exploiting ion migration, back diffusion, and modulable Schottky barriers establishes general design rules for realizing higher-order memristors. This higher order enables complex binocular orientation selectivity in neural networks exploiting the intrinsic physics of the devices, without the need for complicated circuitry.

An energy-efficient in-memory computing architecture for survival data analysis based on resistive switching memories.

One of the objectives fostered in medical science is the so-called precision medicine, which requires the analysis of a large amount of survival data from patients to deeply understand treatment options. Tools like machine learning (ML) and deep neural networks are becoming a de-facto standard. Nowadays, computing facilities based on the Von Neumann architecture are devoted to these tasks, yet rapidly hitting a bottleneck in performance and energy efficiency. The in-memory computing (IMC) architecture emerged as a revolutionary approach to overcome that issue. In this work, we propose an IMC architecture based on resistive switching memory (RRAM) crossbar arrays to provide a convenient primitive for matrix-vector multiplication in a single computational step. This opens massive performance improvement in the acceleration of a neural network that is frequently used in survival analysis of biomedical records, namely the DeepSurv. We explored how the synaptic weights mapping strategy and the programming algorithms developed to counter RRAM non-idealities expose a performance/energy trade-off. Finally, we discussed how this application is tailored for the IMC architecture rather than being executed on commodity systems.

Resistive-switching crossbar memory based on Ni-NiO core-shell nanowires.

Resistive-switching memory (RRAM) is an emerging nanoscale device based on the localized metal-insulator transition within a few-nanometer-sized metal oxide region. RRAM is one of the most promising memory technologies for the ultimate downscaling of nonvolatile memory. However, to develop memory arrays with densities approaching 1 Tb cm(-2) , bottom-up schemes based on synthesis and assembly of metal oxide nanowires (NWs) must be demonstrated. A RRAM memory device based on core-shell Ni-NiO NWs is presented, in which the Ni core plays the role of the metallic interconnect, while the NiO shell serves as the active switching layer. A resistance change of at least two orders of magnitude is shown on electrical operation of the device, and the metal-insulator switching is unequivocally demonstrated to take place in the NiO shell at the crossing between two NWs or between a NW and a gold electrode strip. Since the fabrication of the NW crossbar device is not limited by lithography, this approach may provide a basis for high-density, low-cost crossbar memory with long-term storage stability.

A Brain-Inspired Homeostatic Neuron Based on Phase-Change Memories for Efficient Neuromorphic Computing.

One of the main goals of neuromorphic computing is the implementation and design of systems capable of dynamic evolution with respect to their own experience. In biology, synaptic scaling is the homeostatic mechanism which controls the frequency of neural spikes within stable boundaries for improved learning activity. To introduce such control mechanism in a hardware spiking neural network (SNN), we present here a novel artificial neuron based on phase change memory (PCM) devices capable of internal regulation via homeostatic and plastic phenomena. We experimentally show that this mechanism increases the robustness of the system thus optimizing the multi-pattern learning under spike-timing-dependent plasticity (STDP). It also improves the continual learning capability of hybrid supervised-unsupervised convolutional neural networks (CNNs), in terms of both resilience and accuracy. Furthermore, the use of neurons capable of self-regulating their fire responsivity as a function of the PCM internal state enables the design of dynamic networks. In this scenario, we propose to use the PCM-based neurons to design bio-inspired recurrent networks for autonomous decision making in navigation tasks. The agent relies on neuronal spike-frequency adaptation (SFA) to explore the environment via penalties and rewards. Finally, we show that the conductance drift of the PCM devices, contrarily to the applications in neural network accelerators, can improve the overall energy efficiency of neuromorphic computing by implementing bio-plausible active forgetting.