RESUMO
Neural networks based on memristive devices1-3 have the ability to improve throughput and energy efficiency for machine learning4,5 and artificial intelligence6, especially in edge applications7-21. Because training a neural network model from scratch is costly in terms of hardware resources, time and energy, it is impractical to do it individually on billions of memristive neural networks distributed at the edge. A practical approach would be to download the synaptic weights obtained from the cloud training and program them directly into memristors for the commercialization of edge applications. Some post-tuning in memristor conductance could be done afterwards or during applications to adapt to specific situations. Therefore, in neural network applications, memristors require high-precision programmability to guarantee uniform and accurate performance across a large number of memristive networks22-28. This requires many distinguishable conductance levels on each memristive device, not only laboratory-made devices but also devices fabricated in factories. Analog memristors with many conductance states also benefit other applications, such as neural network training, scientific computing and even 'mortal computing'25,29,30. Here we report 2,048 conductance levels achieved with memristors in fully integrated chips with 256 × 256 memristor arrays monolithically integrated on complementary metal-oxide-semiconductor (CMOS) circuits in a commercial foundry. We have identified the underlying physics that previously limited the number of conductance levels that could be achieved in memristors and developed electrical operation protocols to avoid such limitations. These results provide insights into the fundamental understanding of the microscopic picture of memristive switching as well as approaches to enable high-precision memristors for various applications. Fig. 1 HIGH-PRECISION MEMRISTOR FOR NEUROMORPHIC COMPUTING.: a, Proposed scheme of the large-scale application of memristive neural networks for edge computing. Neural network training is performed in the cloud. The obtained weights are downloaded and accurately programmed into a massive number of memristor arrays distributed at the edge, which imposes high-precision requirements on memristive devices. b, An eight-inch wafer with memristors fabricated by a commercial semiconductor manufacturer. c, High-resolution transmission electron microscopy image of the cross-section view of a memristor. Pt and Ta serve as the bottom electrode (BE) and top electrode (TE), respectively. Scale bars, 1 µm and 100 nm (inset). d, Magnification of the memristor material stack. Scale bar, 5 nm. e, As-programmed (blue) and after-denoising (red) currents of a memristor are read by a constant voltage (0.2 V). The denoising process eliminated the large-amplitude RTN observed in the as-programmed state (see Methods). f, Magnification of three nearest-neighbour states after denoising. The current of each state was read by a constant voltage (0.2 V). No large-amplitude RTN was observed, and all of the states can be clearly distinguished. g, An individual memristor on the chip was tuned into 2,048 resistance levels by high-resolution off-chip driving circuitry, and each resistance level was read by a d.c. voltage sweeping from 0 to 0.2 V. The target resistance was set from 50 µS to 4,144 µS with a 2-µS interval between neighbouring levels. All readings at 0.2 V are less than 1 µS from the target conductance. Bottom inset, magnification of the resistance levels. Top inset, experimental results of an entire 256 × 256 array programmed by its 6-bit on-chip circuitry into 64 32 × 32 blocks, and each block is programmed into one of the 64 conductance levels. Each of the 256 × 256 memristors has been previously switched over one million cycles, demonstrating the high endurance and robustness of the devices.
RESUMO
Memristor-enabled neuromorphic computing systems provide a fast and energy-efficient approach to training neural networks1-4. However, convolutional neural networks (CNNs)-one of the most important models for image recognition5-have not yet been fully hardware-implemented using memristor crossbars, which are cross-point arrays with a memristor device at each intersection. Moreover, achieving software-comparable results is highly challenging owing to the poor yield, large variation and other non-ideal characteristics of devices6-9. Here we report the fabrication of high-yield, high-performance and uniform memristor crossbar arrays for the implementation of CNNs, which integrate eight 2,048-cell memristor arrays to improve parallel-computing efficiency. In addition, we propose an effective hybrid-training method to adapt to device imperfections and improve the overall system performance. We built a five-layer memristor-based CNN to perform MNIST10 image recognition, and achieved a high accuracy of more than 96 per cent. In addition to parallel convolutions using different kernels with shared inputs, replication of multiple identical kernels in memristor arrays was demonstrated for processing different inputs in parallel. The memristor-based CNN neuromorphic system has an energy efficiency more than two orders of magnitude greater than that of state-of-the-art graphics-processing units, and is shown to be scalable to larger networks, such as residual neural networks. Our results are expected to enable a viable memristor-based non-von Neumann hardware solution for deep neural networks and edge computing.
RESUMO
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.
RESUMO
An amendment to this paper has been published and can be accessed via a link at the top of the paper.
RESUMO
With their working mechanisms based on ion migration, the switching dynamics and electrical behaviour of memristive devices resemble those of synapses and neurons, making these devices promising candidates for brain-inspired computing. Built into large-scale crossbar arrays to form neural networks, they perform efficient in-memory computing with massive parallelism by directly using physical laws. The dynamical interactions between artificial synapses and neurons equip the networks with both supervised and unsupervised learning capabilities. Moreover, their ability to interface with analogue signals from sensors without analogue/digital conversions reduces the processing time and energy overhead. Although numerous simulations have indicated the potential of these networks for brain-inspired computing, experimental implementation of large-scale memristive arrays is still in its infancy. This Review looks at the progress, challenges and possible solutions for efficient brain-inspired computation with memristive implementations, both as accelerators for deep learning and as building blocks for spiking neural networks.
Assuntos
Encéfalo , Computadores , Equipamentos e Provisões Elétricas , Redes Neurais de ComputaçãoRESUMO
The accumulation and extrusion of Ca2+ in the pre- and postsynaptic compartments play a critical role in initiating plastic changes in biological synapses. To emulate this fundamental process in electronic devices, we developed diffusive Ag-in-oxide memristors with a temporal response during and after stimulation similar to that of the synaptic Ca2+ dynamics. In situ high-resolution transmission electron microscopy and nanoparticle dynamics simulations both demonstrate that Ag atoms disperse under electrical bias and regroup spontaneously under zero bias because of interfacial energy minimization, closely resembling synaptic influx and extrusion of Ca2+, respectively. The diffusive memristor and its dynamics enable a direct emulation of both short- and long-term plasticity of biological synapses, representing an advance in hardware implementation of neuromorphic functionalities.
RESUMO
A Pt/NbOx/TiOy/NbOx/TiN stack integrated on a 30 nm contact via shows a programming current as low as 10 nA and 1 pA for the set and reset switching, respectively, and a self-rectifying ratio as high as â¼105, which are suitable characteristics for low-power memristor applications. It also shows a forming-free characteristic. A charge-trap-associated switching model is proposed to account for this self-rectifying memrisive behavior. In addition, an asymmetric voltage scheme (AVS) to decrease the write power consumption by utilizing this self-rectifying memristor is also described. When the device is used in a 1000 × 1000 crossbar array with the AVS, the programming power can be decreased to 8.0% of the power consumption of a conventional biasing scheme. If the AVS is combined with a nonlinear selector, a power consumption reduction to 0.31% of the reference value is possible.
RESUMO
The authors of the International Technology Roadmap for Semiconductors-the industry consensus set of goals established for advancing silicon integrated circuit technology-have challenged the computing research community to find new physical state variables (other than charge or voltage), new devices, and new architectures that offer memory and logic functions beyond those available with standard transistors. Recently, ultra-dense resistive memory arrays built from various two-terminal semiconductor or insulator thin film devices have been demonstrated. Among these, bipolar voltage-actuated switches have been identified as physical realizations of 'memristors' or memristive devices, combining the electrical properties of a memory element and a resistor. Such devices were first hypothesized by Chua in 1971 (ref. 15), and are characterized by one or more state variables that define the resistance of the switch depending upon its voltage history. Here we show that this family of nonlinear dynamical memory devices can also be used for logic operations: we demonstrate that they can execute material implication (IMP), which is a fundamental Boolean logic operation on two variables p and q such that pIMPq is equivalent to (NOTp)ORq. Incorporated within an appropriate circuit, memristive switches can thus perform 'stateful' logic operations for which the same devices serve simultaneously as gates (logic) and latches (memory) that use resistance instead of voltage or charge as the physical state variable.
RESUMO
Highly reproducible bipolar resistance switching was recently demonstrated in a composite material of Pt nanoparticles dispersed in silicon dioxide. Here, we examine the electrical performance and scalability of this system and demonstrate devices with ultrafast (<100 ps) switching, long state retention (no measurable relaxation after 6 months), and high endurance (>3 × 10(7) cycles). A possible switching mechanism based on ion motion in the film is discussed based on these observations.
RESUMO
A wide reservoir computing system is an advanced architecture composed of multiple reservoir layers in parallel, which enables more complex and diverse internal dynamics for multiple time-series information processing. However, its hardware implementation has not yet been realized due to the lack of a high-performance physical reservoir and the complexity of fabricating multiple stacks. Here, we achieve a proof-of-principle demonstration of such hardware made of a multilayered three-dimensional stacked 3 × 10 × 10 tungsten oxide memristive crossbar array, with which we further realize a wide physical reservoir computing for efficient learning and forecasting of multiple time-series data. Because a three-layer structure allows the seamless and effective extraction of intricate three-dimensional local features produced by various temporal inputs, it can readily outperform two-dimensional based approaches extensively studied previously. Our demonstration paves the way for wide physical reservoir computing systems capable of efficiently processing multiple dynamic time-series information.
RESUMO
Numerous efforts for emulating organ systems comprised of multiple functional units have driven substantial advancements in bio-realistic electronics and systems. The resistance change behavior observed in diffusive memristors shares similarities with the potential change in biological neurons. Here, the diffusive threshold switching phenomenon in Ag-incorporated organometallic halide perovskites is utilized to demonstrate the functions of afferent neurons. Halide perovskites-based diffusive memristors show a low threshold voltage of ≈0.2 V with little variation, attributed to the facile migration of Ag ions uniformly dispersed within the halide matrix. Based on the reversible and reliable volatile threshold switching, the memristors successfully demonstrate fundamental nociceptive functions including threshold firing, relaxation, and sensitization. Furthermore, to replicate the biological mechano-nociceptive phenomenon at a system level, an artificial mechano-nociceptive system is built by integrating a diffusive memristor with a force-sensing resistor. The presented system is capable of detecting and discerning the detrimental impact caused by a heavy steel ball, effectively exhibiting the corresponding sensitization response. By further extending the single nociceptive system into a 5 × 5 array, successful stereoscopic nociception of uneven impulses is achieved in the artificial skin system through array-scale sensitization. These results represent significant progress in the field of bio-inspired electronics and systems.
RESUMO
Ionic memristor devices are crucial for efficient artificial neural network computations in neuromorphic hardware. They excel in multi-bit implementation but face challenges like device reliability and sneak currents in crossbar array architecture (CAA). Interface-type ionic memristors offer low variation, self-rectification, and no forming process, making them suitable for CAA. However, they suffer from slow weight updates and poor retention and endurance. To address these issues, the study demonstrated an alkali ion self-rectifying memristor with an alkali metal reservoir formed by a bottom electrode design. By adopting Li metal as the adhesion layer of the bottom electrode, an alkali ion reservoir was formed at the bottom of the memristor layer by diffusion occurring during the atomic layer deposition process for the Na:TiO2 memristor layer. In addition, Al dopant was used to improve the retention characteristics by suppressing the diffusion of alkali cations. In the memristor device with optimized Al doping, retention characteristics of more than 20 h at 125 °C, endurance characteristics of more than 5.5 × 105, and high linearity/symmetry of weight update characteristics were achieved. In reliability tests on 100 randomly selected devices from a 32 × 32 CAA device, device-to-device and cycle-to-cycle variations showed low variation values within 81% and 8%, respectively.
RESUMO
In-memory computing represents an effective method for modeling complex physical systems that are typically challenging for conventional computing architectures but has been hindered by issues such as reading noise and writing variability that restrict scalability, accuracy, and precision in high-performance computations. We propose and demonstrate a circuit architecture and programming protocol that converts the analog computing result to digital at the last step and enables low-precision analog devices to perform high-precision computing. We use a weighted sum of multiple devices to represent one number, in which subsequently programmed devices are used to compensate for preceding programming errors. With a memristor system-on-chip, we experimentally demonstrate high-precision solutions for multiple scientific computing tasks while maintaining a substantial power efficiency advantage over conventional digital approaches.
RESUMO
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.
RESUMO
Memristors have attracted increasing attention due to their tremendous potential to accelerate data-centric computing systems. The dynamic reconfiguration of memristive devices in response to external electrical stimuli can provide highly desirable novel functionalities for computing applications when compared with conventional complementary-metal-oxide-semiconductor (CMOS)-based devices. Those most intensively studied and extensively reviewed memristors in the literature so far have been filamentary type memristors, which typically exhibit a relatively large variability from device to device and from switching cycle to cycle. On the other hand, filament-free switching memristors have shown a better uniformity and attractive dynamical properties, which can enable a variety of new computing paradigms but have rarely been reviewed. In this article, a wide range of filament-free switching memristors and their corresponding computing applications are reviewed. Various junction structures, switching properties, and switching principles of filament-free memristors are surveyed and discussed. Furthermore, we introduce recent advances in different computing schemes and their demonstrations based on non-filamentary memristors. This Review aims to present valuable insights and guidelines regarding the key computational primitives and implementations enabled by these filament-free switching memristors.
RESUMO
The increasing interests in analog computing nowadays call for multipurpose analog computing platforms with reconfigurability. The advancement of analog computing, enabled by novel electronic elements like memristors, has shown its potential to sustain the exponential growth of computing demand in the new era of analog data deluge. Here, a platform of a memristive field-programmable analog array (memFPAA) is experimentally demonstrated with memristive devices serving as a variety of core analog elements and CMOS components as peripheral circuits. The memFPAA is reconfigured to implement a first-order band pass filter, an audio equalizer, and an acoustic mixed frequency classifier, as application examples. The memFPAA, featured with programmable analog memristors, memristive routing networks, and memristive vector-matrix multipliers, opens opportunities for fast prototyping analog designs as well as efficient analog applications in signal processing and neuromorphic computing.
RESUMO
Memristive technology has been rapidly emerging as a potential alternative to traditional CMOS technology, which is facing fundamental limitations in its development. Since oxide-based resistive switches were demonstrated as memristors in 2008, memristive devices have garnered significant attention due to their biomimetic memory properties, which promise to significantly improve power consumption in computing applications. Here, we provide a comprehensive overview of recent advances in memristive technology, including memristive devices, theory, algorithms, architectures, and systems. In addition, we discuss research directions for various applications of memristive technology including hardware accelerators for artificial intelligence, in-sensor computing, and probabilistic computing. Finally, we provide a forward-looking perspective on the future of memristive technology, outlining the challenges and opportunities for further research and innovation in this field. By providing an up-to-date overview of the state-of-the-art in memristive technology, this review aims to inform and inspire further research in this field.
RESUMO
Memristors are memory resistors promising a rapid integration into future memory technologies. However, progress is still critically limited by a lack of understanding of the physical processes occurring at the nanoscale. Here we correlate device electrical characteristics with local atomic structure, chemistry and temperature. We resolved a single conducting channel that is made up of a reduced phase of the as-deposited titanium oxide. Moreover, we observed sufficient Joule heating to induce a crystallization of the oxide surrounding the channel, with a peculiar pattern that finite element simulations correlated with the existence of a hot spot close to the bottom electrode, thus identifying the switching location. This work reports direct observations in all three dimensions of the internal structure of titanium oxide memristors.