Brain-inspired Neuromorphic Computing Research Articles

Enhanced Switching Properties in TaOx Memristors Using Diffusion Limiting Layer for Synaptic Learning

To move towards a new generation powerful computing system, brain-inspired neuromorphic computing is expected to transform the architecture of the conventional computer, where memristors are considered to be potential solutions for synapses part. We propose and demonstrate a novel approach to achieve remarkable improvement of analog switching linearity in TaN/Ta/TaO x /Al 2 O 3 /Pt/Si memristors by varying Al 2 O 3 layer thickness. Presence of the Al 2 O 3 layer is confirmed from the Auger Electron Spectroscopy study. Good analog switching ratio of about $100\times $ and superior switching uniformity are observed for the 1 nm Al 2 O 3 based device. Multilevel capability of the memristive devices is also explored for prospective use as a synapse. More than 10 4 and $4\times 10^{4}$ cycles nondegradable dc and ac endurances, respectively, alongwith 10 4 second retention are achieved for the optimized device. Improved linearities of 2.41 and −2.77 for potentiation and depression, respectively are obtained for such 1 nm Al 2 O 3 -based devices. The property of gradual resistance changed by pulse amplitudes confirms that the TaO x memristors can be potentially used as an electronic synapse.

Parallel weight update protocol for a carbon nanotube synaptic transistor array for accelerating neuromorphic computing.

Brain-inspired neuromorphic computing has the potential to overcome the inherent inefficiency of the conventional von Neumann architecture by using the massively parallel processing power of artificial neural networks. Neuromorphic parallel processing can be implemented naturally using the crossbar geometry of synaptic device arrays with Ohm's and Kirchhoff's laws. However, selective and parallel weight updates of the synaptic crossbar array are still very challenging due to the unavoidable crosstalk between adjacent devices and sneak path currents. Here, we experimentally demonstrate a weight update protocol in a carbon nanotube synaptic transistor array, where selective and parallel weight updates can be executed by exploiting the individually controllable three terminals of the synaptic device via a localized carrier trapping mechanism. The trained 9 × 8 synaptic array solves four different convolution operations simultaneously for the feature extraction of an image. The massive parallelism and robustness of the weight update protocol are important features toward effective manipulation of big data through neuromorphic computing systems.

Neuromorphic Computing: A Fully Printed Flexible MoS2 Memristive Artificial Synapse with Femtojoule Switching Energy (Adv. Electron. Mater. 12/2019)

In article number 1900740, Tawfique Hasan, Aaron Thean, Yong-Wei Zhang, Kah-Wee Ang, and co-workers report the demonstration of flexible MoS2 memristive artificial synapses via scalable, low-temperature aerosol-jet printing. Fully printed memristors in a cross-bar structure enable efficient emulation of synaptic plasticity functions with femtojoule energy consumption. This work paves the way toward realizing system-on-plastics for brain-inspired neuromorphic computing.

Multi-spectral gate-triggered heterogeneous photonic neuro-transistors for power-efficient brain-inspired neuromorphic computing

For the realization of low-power consumption brain-inspired neuromorphic computing devices which mimic the biological neuronal information processing methodology, the development of photonic transistors capable of synaptic behaviors and neuronal computation have attracted lots of interests. Here, metal-chalcogenide (MC)/metal-oxide (MO) heterogeneous photonic neuro-transistors capable of multi-spectrum triggered synaptic responses and corresponding neuronal computation were developed for an intelligent and energy efficient neuromorphic device. The photonic transistor architecture including a solution-processed broadband photo-active heterogeneous channel and electronic modulatory terminal enable to establish power-saved multi-level writing/reading processing. The multi-spectral gate-triggerings and their synaptic responses were emulated via the broadband absorbing MC/MO heterogeneous semiconducting structure and its defective hetero-interface, which can be fine-tuned by varying photo-spectrum of applied spikes and controlling of interfacial traps in-between, respectively. More importantly, the multi-spectrum triggered heterogeneous photonic neuro-transistors can facilitate wider dynamic and more intelligent neuronal computation such as multi-level dendritic summation and fire behaviors, logic-computation, and associated learning beyond conventional simple synaptic-level photonic devices. The results reported here argue that the multi-spectral activated heterogeneous photonic neuro-transistor outperforms current state-of-neuro-devices, provide a facile and generic route to achieve high-density and energy efficient neuromorphic system.

Flexible Transparent Organic Artificial Synapse Based on the Tungsten/Egg Albumen/Indium Tin Oxide/Polyethylene Terephthalate Memristor.

As artificial synapses in biomimetics, memristors have received increasing attention because of their great potential in brain-inspired neuromorphic computing. The use of biocompatible and degradable materials as the active resistive layer is promising in memristor fabrication. In this work, we select egg albumen as the resistive layer to fabricate flexible tungsten/egg albumen/indium tin oxide/polyethylene terephthalate devices, which can operate normally under mechanical bending without significant performance degradation. This proposed memristor device exhibits a transparency of more than 90% under visible light with a wavelength range of 230-850 nm. Moreover, by changing amplitudes of pulse voltage instead of intervals, paired-pulse facilitation can be transmitted to paired-pulse depression, which can faithfully mimic dynamical balance of Ca2+ concentration shaped by voltage-sensitive calcium channels. The device resistance can be modulated gradually by applied pulse trains to mimic certain neural bionic behaviors, including excitatory postsynaptic current, short-term plasticity (STP) and long-term plasticity (LTP), and transitions between STP and LTP. The reasons behind these behaviors are analyzed through power consumption calculation. Excellent biosimulation characteristics have been demonstrated in this egg albumen-based memristor device, which is desirable in biocompatible and dissolvable electronics for flexible artificial neuromorphic systems.

A versatile neuromorphic system based on simple neuron model

Brain-inspired neuromorphic computing has attracted much attention for its advanced computing concept. However, the massive hardware cost in fully-connected architectures makes it challenging to build a large-scale neuromorphic system. In this work, we report a compact, programmable, versatile, and scalable neuromorphic architecture. To demonstrate the concept of the neuromorphic architecture, a neuromorphic system consisting of four cores is implemented on an FPGA platform. On the one hand, the neuromorphic system is extremely compact and hardware-saving. The computing block based on a simple digital leaky Integrate-and-Fire (LIF) model only costs 69 logic elements (LEs); only one physical neuron is implemented in each core, and it can be reused as hundreds of virtual neurons by time-division-multiplexing; only four 9-bit synaptic weights are assigned to each neuron, which effectively alleviates the hardware explosion in fully-connected architecture. On the other hand, the neuromorphic system is programmable and versatile, and can perform different neural network computing. The neuromorphic system mapped with a three-layer feedforward network successfully recognizes the MNIST handwritten digits with an accuracy of 96.26%, and it also effectively realizes different convolution operations which are basic computing operations in convolutional neural networks. Last but not least, each neuromorphic core has its own router module, making it convenient to scale up.

Synapse behavior characterization and physical mechanism of a TiN/SiOx/p-Si tunneling memristor device

The demand for massive deep learning neural networks has driven the development of nanoscale memristor devices, which perform brain-inspired neuromorphic computing.

Flexible Electronic Synapses for Face Recognition Application with Multimodulated Conductance States.

An artificial synaptic device with a continuous weight modulation behavior is fundamental to the hardware implementation of the bioinspired neuromorphic systems. Recent reported synaptic devices have a less number of conductance states, which is not beneficial for the continuous modulation of weights in neuromorphic computing. Preparing a device with as many conductance states as possible is of great significance to the development of brain-inspired neuromorphic computing. Here, we present a two-terminal flexible organic synaptic device with ultra-multimodulated conductance states, realizing a face recognition functionality with a strong error-tolerant nature for the first time. The device shows an excellent long-term potentiation or long-term depression behavior and reliability after 1000 folded destructive tests. There are 600 continuous ultra-multimodulated conductance states, which can be used to realize the great face recognition capability. The recognition rates were 95.2% and above 90% for the initial and 15% noise pixel images, respectively. The strong error-tolerant nature indicates a potential application of a flexible organic artificial synaptic device with ultra-multimodulated conductance states in the large-scale neuromorphic systems.

Low-Power, Electrochemically Tunable Graphene Synapses for Neuromorphic Computing.

Brain-inspired neuromorphic computing has the potential to revolutionize the current computing paradigm with its massive parallelism and potentially low power consumption. However, the existing approaches of using digital complementary metal-oxide-semiconductor devices (with "0" and "1" states) to emulate gradual/analog behaviors in the neural network are energy intensive and unsustainable; furthermore, emerging memristor devices still face challenges such as nonlinearities and large write noise. Here, an electrochemical graphene synapse, where the electrical conductance of graphene is reversibly modulated by the concentration of Li ions between the layers of graphene is presented. This fundamentally different mechanism allows to achieve a good energy efficiency (<500 fJ per switching event), analog tunability (>250 nonvolatile states), good endurance, and retention performances, and a linear and symmetric resistance response. Essential neuronal functions such as excitatory and inhibitory synapses, long-term potentiation and depression, and spike timing dependent plasticity with good repeatability are demonstrated. The scaling study suggests that this simple, two-dimensional synapse is scalable in terms of switching energy and speed.

Diverse spike-timing-dependent plasticity based on multilevel HfO x memristor for neuromorphic computing

Memristors have emerged as promising candidates for artificial synaptic devices, serving as the building block of brain-inspired neuromorphic computing. In this letter, we developed a Pt/HfO x /Ti memristor with nonvolatile multilevel resistive switching behaviors due to the evolution of the conductive filaments and the variation in the Schottky barrier. Diverse state-dependent spike-timing-dependent-plasticity (STDP) functions were implemented with different initial resistance states. The measured STDP forms were adopted as the learning rule for a three-layer spiking neural network which achieves a 75.74% recognition accuracy for MNIST handwritten digit dataset. This work has shown the capability of memristive synapse in spiking neural networks for pattern recognition application.

Short-Term and Long-Term Plasticity Mimicked in Low-Voltage Ag/GeSe/TiN Electronic Synapse

The electronic synapse, which can vividly emulate short-term and long-term plasticity, as well as voltage sensitivity, in the bio-synapse, is the vital device foundation for brain-inspired neuromorphic computing. In this letter, we propose a Ag/GeSe/TiN memristor as an electronic synapse for brain-inspired neuromorphic applications. Due to the electromigration and diffusion of Ag cation, the volatile and non-volatile switching behaviours are coexistent in this device. Various synaptic functions, including short-term plasticity, long-term plasticity, pair-pulse facilitation, and spike timing-dependent plasticity, have been successfully eliminated in Ag/GeSe/TiN devices. Furthermore, all the synaptic functions are induced by the spiking stimuli with amplitudes of several hundred millivolts. All the results demonstrate that the Ag/GeSe/TiN device has great potential for brain-inspired computing systems in the future.

Dendritic-Inspired Processing Enables Bio-Plausible STDP in Compound Binary Synapses

Brain-inspired learning mechanisms, e.g. spike timing dependent plasticity (STDP), enable agile and fast on-the-fly adaptation capability in a spiking neural network. When incorporating emerging nanoscale resistive non-volatile memory (NVM) devices, with ultra-low power consumption and high-density integration capability, a spiking neural network hardware would result in several orders of magnitude reduction in energy consumption at a very small form factor and potentially herald autonomous learning machines. However, actual memory devices have shown to be intrinsically binary with stochastic switching, and thus impede the realization of ideal STDP with continuous analog values. In this work, a dendritic-inspired processing architecture is proposed in addition to novel CMOS neuron circuits. The utilization of spike attenuations and delays transforms the traditionally undesired stochastic behavior of binary NVMs into a useful leverage that enables biologically-plausible STDP learning. As a result, this work paves a pathway to adopt practical binary emerging NVM devices in brain-inspired neuromorphic computing.

Ultra-low power Hf0.5Zr0.5O2 based ferroelectric tunnel junction synapses for hardware neural network applications.

Brain-inspired neuromorphic computing has shown great promise beyond the conventional Boolean logic. Nanoscale electronic synapses, which have stringent demands for integration density, dynamic range, energy consumption, etc., are key computational elements of the brain-inspired neuromorphic system. Ferroelectric tunneling junctions have been shown to be ideal candidates to realize the functions of electronic synapses due to their ultra-low energy consumption and the nature of ferroelectric tunneling. Here, we report a new electronic synapse based on a three-dimensional vertical Hf0.5Zr0.5O2-based ferroelectric tunneling junction that meets the full functions of biological synapses. The fabricated three-dimensional vertical ferroelectric tunneling junction synapse (FTJS) exhibits high integration density and excellent performances, such as analog-like conductance transition under a training scheme, low energy consumption of synaptic weight update (1.8 pJ per spike) and good repeatability (>103 cycles). In addition, the implementation of pattern training in hardware with strong tolerance to input faults and variations is also illustrated in the 3D vertical FTJS array. Furthermore, pattern classification and recognition are achieved, and these results demonstrate that the Hf0.5Zr0.5O2-based FTJS has high potential to be an ideal electronic component for neuromorphic system applications.

Proposal for a Leaky-Integrate-Fire Spiking Neuron Based on Magnetoelectric Switching of Ferromagnets

The efficiency of the human brain in performing classification tasks has attracted considerable research interest in brain-inspired neuromorphic computing. The spiking neuromorphic architectures attempt to mimic the computations performed in the brain through a dense interconnection of the neurons and synaptic weights. A leaky-integrate-fire (LIF) spiking model is widely used to emulate the dynamics of the biological neurons. In this paper, we propose a spin-based LIF spiking neuron using the magnetoelectric (ME) switching of ferromagnets. The voltage across the ME oxide exhibits a typical leaky-integrate behavior, which in turn switches an underlying ferromagnet. Due to the effect of thermal noise, the ferromagnet exhibits probabilistic switching dynamics, which is reminiscent of the stochasticity exhibited by biological neurons. The energy efficiency of the ME switching mechanism coupled with the intrinsic nonvolatility of ferromagnets results in lower energy consumption, when compared with a CMOS LIF neuron. A device to system-level simulation framework has been developed to investigate the feasibility of the proposed LIF neuron for a hand-written digit recognition application.

Engineering incremental resistive switching in TaOx based memristors for brain-inspired computing.

Brain-inspired neuromorphic computing is expected to revolutionize the architecture of conventional digital computers and lead to a new generation of powerful computing paradigms, where memristors with analog resistive switching are considered to be potential solutions for synapses. Here we propose and demonstrate a novel approach to engineering the analog switching linearity in TaOx based memristors, that is, by homogenizing the filament growth/dissolution rate via the introduction of an ion diffusion limiting layer (DLL) at the TiN/TaOx interface. This has effectively mitigated the commonly observed two-regime conductance modulation behavior and led to more uniform filament growth (dissolution) dynamics with time, therefore significantly improving the conductance modulation linearity that is desirable in neuromorphic systems. In addition, the introduction of the DLL also served to reduce the power consumption of the memristor, and important synaptic learning rules in biological brains such as spike timing dependent plasticity were successfully implemented using these optimized devices. This study could provide general implications for continued optimizations of memristor performance for neuromorphic applications, by carefully tuning the dynamics involved in filament growth and dissolution.