Ultralow-Power Machine Vision with Self-Powered Sensor Reservoir

Ultralow Power In-Sensor Neuronal Computing with Oscillatory Retinal Neurons for Frequency-Multiplexed, Parallel Machine Vision

In-sensor and near-sensor computing architectures enable multiply accumulate operations to be carried out directly at the point of sensing. In-sensor architectures offer dramatic power and speed improvements over traditional von Neumann architectures by eliminating multiple analog-to-digital conversions, data storage, and data movement operations. Current in-sensor processing approaches rely on tunable sensors or additional weighting elements to perform linear functions such as multiply accumulate operations as the sensor acquires data. This work implements in-sensor computing with an oscillatory retinal neuron device that converts incident optical signals into voltage oscillations. A computing scheme is introduced based on the frequency shift of coupled oscillators that enables parallel, frequency multiplexed, nonlinear operations on the inputs. An experimentally implemented 3 × 3 focal plane array of coupled neurons shows that functions approximating edge detection, thresholding, and segmentation occur in parallel. An example of inference on handwritten digits from the MNIST database is also experimentally demonstrated with a 3 × 3 array of coupled neurons feeding into a single hidden layer neural network, approximating a liquid-state machine. Finally, the equivalent energy consumption to carry out image processing operations, including peripherals such as the Fourier transform circuits, is projected to be <20 fJ/OP, possibly reaching as low as 15 aJ/OP.

Si/CuO Heterojunction-Based Photomemristor for Reconfigurable, Non-Volatile, and Self-Powered In-Sensor Computing

In-sensor computing has attracted considerable interest as a solution for overcoming the energy efficiency and response time limitations of the traditional von Neumann architecture. Recently, emerging memristors based on transition-metal oxides (TMOs) have attracted attention as promising candidates for in-memory computing owing to their tunable conductance, high speed, and low operational energy. However, the poor photoresponse of TMOs presents challenges for integrating sensing and processing units into a single device. This integration is crucial for eliminating the need for a sensor/processor interface and achieving energy-efficient in-sensor computing systems. In this study, a Si/CuO heterojunction-based photomemristor is proposed that combines the reversible resistive switching behavior of CuO with the appropriate optical absorption bandgap of the Si substrate. The proposed photomemristor demonstrates a simultaneous reconfigurable, non-volatile, and self-powered photoresponse, producing a microampere-level photocurrent at zero bias. The controlled migration of oxygen vacancies in CuO result in distinct energy-band bending at the interface, enabling multiple levels of photoresponsivity. Additionally, the device exhibits high stability and ultrafast response speed to the built-in electric field. Furthermore, the prototype photomemristor can be trained to emulate the attention-driven nature of the human visual system, indicating the tremendous potential of TMO-based photomemristors as hardware foundations for in-sensor computing.

Gate-Tunable Positive and Negative Photoconductance in Near-Infrared Organic Heterostructures for In-Sensor Computing

The rapid growth of sensor data in the artificial intelligence often causes significant reductions in processing speed and power efficiency. Addressing this challenge, in-sensor computing is introduced as an advanced sensor architecture that simultaneously senses, memorizes, and processes images at the sensor level. However, this is rarely reported for organic semiconductors that possess inherent flexibility and tunable bandgap. Herein, an organic heterostructure that exhibits a robust photoresponse to near-infrared (NIR) light is introduced, making it ideal for in-sensor computing applications. This heterostructure, consisting of partially overlapping p-type and n-type organic thin films, is compatible with conventional photolithography techniques, allowing for high integration density of up to 520 devices cm-2 with a 5 µm channel length. Importantly, by modulating gate voltage, both positive and negative photoresponses to NIR light (1050 nm) are attained, which establishes a linear correlation between responsivity and gate voltage and consequently enables real-time matrix multiplication within the sensor. As a result, this organic heterostructure facilitates efficient and precise NIR in-sensor computing, including image processing and nondestructive reading and classification, achieving a recognition accuracy of 97.06%. This work serves as a foundation for the development of reconfigurable and multifunctional NIR neuromorphic vision systems.

New-Generation Ferroelectric AlScN Materials

Ferroelectrics have great potential in the field of nonvolatile memory due to programmable polarization states by external electric field in nonvolatile manner. However, complementary metal oxide semiconductor compatibility and uniformity of ferroelectric performance after size scaling have always been two thorny issues hindering practical application of ferroelectric memory devices. The emerging ferroelectricity of wurtzite structure nitride offers opportunities to circumvent the dilemma. This review covers the mechanism of ferroelectricity and domain dynamics in ferroelectric AlScN films. The performance optimization of AlScN films grown by different techniques is summarized and their applications for memories and emerging in-memory computing are illustrated. Finally, the challenges and perspectives regarding the commercial avenue of ferroelectric AlScN are discussed.

Toward Intelligent Display with Neuromorphic Technology

In the era of the Internet and the Internet of Things, display technology has evolved significantly toward full-scene display and realistic display. Incorporating "intelligence" into displays is a crucial technical approach to meet the demands of this development. Traditional display technology relies on distributed hardware systems to achieve intelligent displays but encounters challenges stemming from the physical separation of sensing, processing, and light-emitting modules. The high energy consumption and data transformation delays limited the development of intelligence display, breaking the physical separation is crucial to overcoming the bottlenecks of intelligence display technology. Inspired by the biological neural system, neuromorphic technology with all-in-one features is widely employed across various fields. It proves effective in reducing system power consumption, facilitating frequent data transformation, and enabling cross-scene integration. Neuromorphic technology shows great potential to overcome display technology bottlenecks, realizing the full-scene display and realistic display with high efficiency and low power consumption. This review offers a comprehensive summary of recent advancements in the application of neuromorphic technology in displays, with a focus on interoperability. This work delves into its state-of-the-art designs and potential future developments aimed at revolutionizing display technology.

All-Photolithography Fabrication of Ion-Gated Flexible Organic Transistor Array for Multimode Neuromorphic Computing

Organic ion-gated transistors (OIGTs) demonstrate commendable performance for versatile neuromorphic systems. However, due to the fragility of organic materials to organic solvents, efficient and reliable all-photolithography methods for scalable manufacturing of high-density OIGT arrays with multimode neuromorphic functions are still missing, especially when all active layers are patterned in high-density. Here, a flexible high-density (9662 devices per cm2) OIGT array with high yield and minimal device-to-device variation is fabricated by a modified all-photolithography method. The unencapsulated flexible array can withstand 1000 times' bending at a radius of 1 mm, and 3 months' storage test in air, without obvious performance degradation. More interesting, the OIGTs can be configured between volatile and nonvolatile modes, suitable for constructing reservoir computing systems to achieve high accuracy in classifying handwritten digits with low training costs. This work proposes a promising design of organic and flexible electronics for affordable neuromorphic systems, encompassing both array and algorithm aspects.

Ultralow-power optoelectronic synaptic transistors based on polyzwitterion dielectrics for in-sensor reservoir computing

Bio-inspired transistor synapses use solid electrolytes to achieve low-power operation and rich synaptic behaviors via ion diffusion and trapping. While these neuromorphic devices hold great promise, they still suffer from challenges such as high leakage currents and power consumption, electrolysis risk, and irreversible conductance changes due to long-range ion migrations and permanent ion trapping. In addition, their response to light is generally limited because of "exciton-polaron quenching", which restricts their potential in in-sensor neuromorphic visions. To address these issues, we propose replacing solid electrolytes with polyzwitterions, where the cation and anion are covalently concatenated via a flexible alkyl chain, thus preventing long-range ion migrations while inducing good photoresponses to the transistors via interfacial charge trapping. Our detailed studies reveal that polyzwitterion-based transistors exhibit optoelectronic synaptic behavior with ultralow-power consumption (~250 aJ per spike) and enable high-performance in-sensor reservoir computing, achieving 95.56% accuracy in perceiving the trajectory of moving basketballs.

A bionic self-driven retinomorphic eye with ionogel photosynaptic retina

Bioinspired bionic eyes should be self-driving, repairable and conformal to arbitrary geometries. Such eye would enable wide-field detection and efficient visual signal processing without requiring external energy, along with retinal transplantation by replacing dysfunctional photoreceptors with healthy ones for vision restoration. A variety of artificial eyes have been constructed with hemispherical silicon, perovskite and heterostructure photoreceptors, but creating zero-powered retinomorphic system with transplantable conformal features remains elusive. By combining neuromorphic principle with retinal and ionoelastomer engineering, we demonstrate a self-driven hemispherical retinomorphic eye with elastomeric retina made of ionogel heterojunction as photoreceptors. The receptor driven by photothermoelectric effect shows photoperception with broadband light detection (365 to 970 nm), wide field-of-view (180°) and photosynaptic (paired-pulse facilitation index, 153%) behaviors for biosimilar visual learning. The retinal photoreceptors are transplantable and conformal to any complex surface, enabling visual restoration for dynamic optical imaging and motion tracking.

Task-Adaptive Neuromorphic Computing Using Reconfigurable Organic Neuristors with Tunable Plasticity and Logic-in-Memory Operations

The brain's function can be dynamically reconfigured through a unified neuron-synapse architecture, enabling task-adaptive network-level topology for energy-efficient learning and inferencing. Here, we demonstrate an organic neuristor utilizing a ferroelectric-electrolyte dielectric interface. This neuristor enables tunable short- to long-term plasticity and reconfigurable logic-in-memory functions by controlling the interfacial interaction between electrolyte ions and ferroelectric dipoles. Notably, the short-term plasticity of the organic neuristor allows for power-efficient reservoir computing in edge-computing scenarios, exhibiting impressive recognition accuracy, including images (90.6%) and acoustic signals (97.7%). For high-performance computing tasks, the neuristor based on long-term plasticity and logic-in-memory operations can construct all of the hardware circuits of a binarized neural network (BNN) within a unified framework. The BNN demonstrates excellent noise tolerance, achieving high recognition accuracies of 99.2% and 86.4% on the MNIST and CIFAR-10 data sets, respectively. Consequently, our research sheds light on the development of power-efficient artificial intelligence systems.

Technology and Integration Roadmap for Optoelectronic Memristor

Optoelectronic memristors (OMs) have emerged as a promising optoelectronic Neuromorphic computing paradigm, opening up new opportunities for neurosynaptic devices and optoelectronic systems. These OMs possess a range of desirable features including minimal crosstalk, high bandwidth, low power consumption, zero latency, and the ability to replicate crucial neurological functions such as vision and optical memory. By incorporating large-scale parallel synaptic structures, OMs are anticipated to greatly enhance high-performance and low-power in-memory computing, effectively overcoming the limitations of the von Neumann bottleneck. However, progress in this field necessitates a comprehensive understanding of suitable structures and techniques for integrating low-dimensional materials into optoelectronic integrated circuit platforms. This review aims to offer a comprehensive overview of the fundamental performance, mechanisms, design of structures, applications, and integration roadmap of optoelectronic synaptic memristors. By establishing connections between materials, multilayer optoelectronic memristor units, and monolithic optoelectronic integrated circuits, this review seeks to provide insights into emerging technologies and future prospects that are expected to drive innovation and widespread adoption in the near future.

Toward a Brain-Neuromorphics Interface

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

Hierarchies in Visual Pathway: Functions and Inspired Artificial Vision

The development of artificial intelligence has posed a challenge to machine vision based on conventional complementary metal-oxide semiconductor (CMOS) circuits owing to its high latency and inefficient power consumption originating from the data shuffling between memory and computation units. Gaining more insights into the function of every part of the visual pathway for visual perception can bring the capabilities of machine vision in terms of robustness and generality. Hardware acceleration of more energy-efficient and biorealistic artificial vision highly necessitates neuromorphic devices and circuits that are able to mimic the function of each part of the visual pathway. In this paper, we review the structure and function of the entire class of visual neurons from the retina to the primate visual cortex within reach (Chapter 2) are reviewed. Based on the extraction of biological principles, the recent hardware-implemented visual neurons located in different parts of the visual pathway are discussed in detail in Chapters 3 and 4. Furthermore, valuable applications of inspired artificial vision in different scenarios (Chapter 5) are provided. The functional description of the visual pathway and its inspired neuromorphic devices/circuits are expected to provide valuable insights for the design of next-generation artificial visual perception systems.

Optoelectronic synapses based on a triple cation perovskite and Al/MoO3 interface for neuromorphic information processing

Optoelectronic synaptic transistors are attractive for applications in next-generation brain-like computation systems, especially for their visible-light operation and in-sensor computing capabilities. However, from a material perspective, it is difficult to build a device that meets expectations in terms of both its functions and power consumption, prompting the call for greater innovation in materials and device construction. In this study, we innovatively combined a novel perovskite carrier supply layer with an Al/MoO3 interface carrier regulatory layer to fabricate optoelectronic synaptic devices, namely Al/MoO3/CsFAMA/ITO transistors. The device could mimic a variety of biological synaptic functions and required ultralow-power consumption during operation with an ultrafast speed of >0.1 μs under an optical stimulus of about 3 fJ, which is equivalent to biological synapses. Moreover, Pavlovian conditioning and visual perception tasks could be implemented using the spike-number-dependent plasticity (SNDP) and spike-rate-dependent plasticity (SRDP). This study suggests that the proposed CsFAMA synapse with an Al/MoO3 interface has the potential for ultralow-power neuromorphic information processing.

Energy-Efficient ReS2-Based Optoelectronic Synapse for 3D Object Reconstruction and Recognition

The neuromorphic vision system (NVS) equipped with optoelectronic synapses integrates perception, storage, and processing and is expected to address the issues of traditional machine vision. However, owing to their lack of stereo vision, existing NVSs focus on 2D image processing, which makes it difficult to solve problems such as spatial cognition errors and low-precision interpretation. Consequently, inspired by the human visual system, an NVS with stereo vision is developed to achieve 3D object recognition, depending on the prepared ReS2 optoelectronic synapse with 12.12 fJ ultralow power consumption. This device exhibits excellent optical synaptic plasticity derived from the persistent photoconductivity effect. As the cornerstone for 3D vision, color planar information is successfully discriminated and stored in situ at the sensor end, benefiting from its wavelength-dependent plasticity in the visible region. Importantly, the dependence of the channel conductance on the target distance is experimentally revealed, implying that the structure information on the object can be directly captured and stored by the synapse. The 3D image of the object is successfully reconstructed via fusion of its planar and depth images. Therefore, the proposed 3D-NVS based on ReS2 synapses for 3D objects achieves a recognition accuracy of 97.0%, which is much higher than that for 2D objects (32.6%), demonstrating its strong ability to prevent 2D-photo spoofing in applications such as face payment, entrance guard systems, and others.

Ferroelectric-defined reconfigurable homojunctions for in-memory sensing and computing

Recently, the increasing demand for data-centric applications is driving the elimination of image sensing, memory and computing unit interface, thus promising for latency- and energy-strict applications. Although dedicated electronic hardware has inspired the development of in-memory computing and in-sensor computing, folding the entire signal chain into one device remains challenging. Here an in-memory sensing and computing architecture is demonstrated using ferroelectric-defined reconfigurable two-dimensional photodiode arrays. High-level cognitive computing is realized based on the multiplications of light power and photoresponsivity through the photocurrent generation process and Kirchhoff's law. The weight is stored and programmed locally by the ferroelectric domains, enabling 51 (>5 bit) distinguishable weight states with linear, symmetric and reversible manipulation characteristics. Image recognition can be performed without any external memory and computing units. The three-in-one paradigm, integrating high-level computing, weight memorization and high-performance sensing, paves the way for a computing architecture with low energy consumption, low latency and reduced hardware overhead.

A Dual-Functional Perovskite-Based Photodetector and Memristor for Visual Memory

The imitation of human visual memory demands the multifunctional integration of light sensors similar to the eyes, and image memory, similar to the brain. Although humans have already implemented electronic devices with visual memory functions, these devices require a combination of various components and logical circuits. However, the combination of visual perception and high-performance information storage capabilities into a single device to achieve visual memory remains challenging. In this study, inspired by the function of human visual memory, a dual-functional perovskite-based photodetector (PD) and memristor are designed to realize visual perception and memory capacities. As a PD, it realizes an ultrahigh self-powered responsivity of 276 mA W-1 , a high detectivity of 4.7 × 1011  Jones (530 nm; light intensities, 2.34 mW cm-2 ), and a high rectification ratio of ≈100 (±2 V). As a memristor, an ultrahigh on/off ratio (≈105 ), an ultralow power consumption of 3 × 10-11  W, a low setting voltage (0.15 V), and a long retention time (>7000 s) are realized. Moreover, the dual-functional device has the capacity to perceive and remember light paths and store data with good cyclic stability. This device exhibits perceptual and cyclic erasable memory functions, which provides new opportunities for mimicking human visual memory in future multifunctional applications.

Achieving reinforcement learning in a three-active-terminal neuromorphic device based on a 2D vdW ferroelectric material

Currently, for most three-terminal neuromorphic devices, only the gate terminal is active. The inadequate modes and freedom of modulation in such devices greatly hinder the implementation of complex neural behaviors and brain-like thinking strategies in hardware systems. Taking advantage of the unique feature of co-existing in-plane (IP) and out-of-plane (OOP) ferroelectricity in two-dimensional (2D) ferroelectric α-In2Se3, we construct a three-active-terminal neuromorphic device where any terminal can modulate the conductance state. Based on the co-operation mode, controlling food intake as a complex nervous system-level behavior is achieved to carry out positive and negative feedback. Specifically, reinforcement learning as a brain-like thinking strategy is implemented due to the coupling between polarizations in different directions. Compared to the single modulation mode, the chance of the agent successfully obtaining the reward in the Markov decision process is increased from 68% to 82% under the co-operation mode through the coupling effect between IP and OOP ferroelectricity in 2D α-In2Se3 layers. Our work demonstrates the practicability of three-active-terminal neuromorphic devices in handling complex tasks and advances a significant step towards implementing brain-like learning strategies based on neuromorphic devices for dealing with real-world challenges.

All-ferroelectric implementation of reservoir computing

Reservoir computing (RC) offers efficient temporal information processing with low training cost. All-ferroelectric implementation of RC is appealing because it can fully exploit the merits of ferroelectric memristors (e.g., good controllability); however, this has been undemonstrated due to the challenge of developing ferroelectric memristors with distinctly different switching characteristics specific to the reservoir and readout network. Here, we experimentally demonstrate an all-ferroelectric RC system whose reservoir and readout network are implemented with volatile and nonvolatile ferroelectric diodes (FDs), respectively. The volatile and nonvolatile FDs are derived from the same Pt/BiFeO₃/SrRuO₃ structure via the manipulation of an imprint field (E_imp). It is shown that the volatile FD with E_imp exhibits short-term memory and nonlinearity while the nonvolatile FD with negligible E_imp displays long-term potentiation/depression, fulfilling the functional requirements of the reservoir and readout network, respectively. Hence, the all-ferroelectric RC system is competent for handling various temporal tasks. In particular, it achieves an ultralow normalized root mean square error of 0.017 in the Hénon map time-series prediction. Besides, both the volatile and nonvolatile FDs demonstrate long-term stability in ambient air, high endurance, and low power consumption, promising the all-ferroelectric RC system as a reliable and low-power neuromorphic hardware for temporal information processing.

Emerging Memtransistors for Neuromorphic System Applications: A Review

The von Neumann architecture with separate memory and processing presents a serious challenge in terms of device integration, power consumption, and real-time information processing. Inspired by the human brain that has highly parallel computing and adaptive learning capabilities, memtransistors are proposed to be developed in order to meet the requirement of artificial intelligence, which can continuously sense the objects, store and process the complex signal, and demonstrate an "all-in-one" low power array. The channel materials of memtransistors include a range of materials, such as two-dimensional (2D) materials, graphene, black phosphorus (BP), carbon nanotubes (CNT), and indium gallium zinc oxide (IGZO). Ferroelectric materials such as P(VDF-TrFE), chalcogenide (PZT), HfxZr1-xO2(HZO), In2Se3, and the electrolyte ion are used as the gate dielectric to mediate artificial synapses. In this review, emergent technology using memtransistors with different materials, diverse device fabrications to improve the integrated storage, and the calculation performance are demonstrated. The different neuromorphic behaviors and the corresponding mechanisms in various materials including organic materials and semiconductor materials are analyzed. Finally, the current challenges and future perspectives for the development of memtransistors in neuromorphic system applications are presented.

High-Contrast Bidirectional Optoelectronic Synapses based on 2D Molecular Crystal Heterojunctions for Motion Detection

Light-stimulated optoelectronic synaptic devices are fundamental compositions of the neuromorphic vision system. However, there are still huge challenges to achieving both bidirectional synaptic behaviors under light stimuli and high performance. Herein, a bilayer 2D molecular crystal (2DMC) p-n heterojunction is developed to achieve high-performance bidirectional synaptic behaviors. The 2DMC heterojunction-based field effect transistor (FET) devices exhibit typical ambipolar properties and remarkable responsivity (R) of 3.58×10⁴ A W^-1 under weak light as low as 0.008 mW cm^-2 . Excitatory and inhibitory synaptic behaviors are successfully realized by the same light stimuli under different gate voltages. Moreover, a superior contrast ratio (CR) of 1.53×10³ is demonstrated by the ultrathin and high-quality 2DMC heterojunction, which transcends previous optoelectronic synapses and enables application for the motion detection of the pendulum. Furthermore, a motion detection network based on the device is developed to detect and recognize classic motion vehicles in road traffic with an accuracy exceeding 90%. This work provides an effective strategy for developing high-contrast bidirectional optoelectronic synapses and shows great potential in the intelligent bionic device and future artificial vision.

Ultralow-power in-memory computing based on ferroelectric memcapacitor network

Analog storage through synaptic weights using conductance in resistive neuromorphic systems and devices inevitably generates harmful heat dissipation. This thermal issue not only limits the energy efficiency but also hampers the very-large-scale and highly complicated hardware integration as in the human brain. Here we demonstrate that the synaptic weights can be simulated by reconfigurable non-volatile capacitances of a ferroelectric-based memcapacitor with ultralow-power consumption. The as-designed metal/ferroelectric/metal/insulator/semiconductor memcapacitor shows distinct 3-bit capacitance states controlled by the ferroelectric domain dynamics. These robust memcapacitive states exhibit uniform maintenance of more than 104 s and well endurance of 109 cycles. In a wired memcapacitor crossbar network hardware, analog vector-matrix multiplication is successfully implemented to classify 9-pixel images by collecting the sum of displacement currents (I = C × dV/dt) in each column, which intrinsically consumes zero energy in memcapacitors themselves. Our work sheds light on an ultralow-power neural hardware based on ferroelectric memcapacitors.

Near-Sensor Reservoir Computing for Gait Recognition via a Multi-Gate Electrolyte-Gated Transistor

The recent emergence of various smart wearable electronics has furnished the rapid development of human-computer interaction, medical health monitoring technologies, etc. Unfortunately, processing redundant motion and physiological data acquired by multiple wearable sensors using conventional off-site digital computers typically result in serious latency and energy consumption problems. In this work, a multi-gate electrolyte-gated transistor (EGT)-based reservoir device for efficient multi-channel near-sensor computing is reported. The EGT, exhibiting rich short-term dynamics under voltage modulation, can implement nonlinear parallel integration of the time-series signals thus extracting the temporal features such as the synchronization state and collective frequency in the inputs. The flexible EGT integrated with pressure sensors can perform on-site gait information analysis, enabling the identification of motion behaviors and Parkinson's disease. This near-sensor reservoir computing system offers a new route for rapid analysis of the motion and physiological signals with significantly improved efficiency and will lead to robust smart flexible wearable electronics.

Dynamic machine vision with retinomorphic photomemristor-reservoir computing

Dynamic machine vision requires recognizing the past and predicting the future of a moving object based on present vision. Current machine vision systems accomplish this by processing numerous image frames or using complex algorithms. Here, we report motion recognition and prediction in recurrent photomemristor networks. In our system, a retinomorphic photomemristor array, working as dynamic vision reservoir, embeds past motion frames as hidden states into the present frame through inherent dynamic memory. The informative present frame facilitates accurate recognition of past and prediction of future motions with machine learning algorithms. This in-sensor motion processing capability eliminates redundant data flows and promotes real-time perception of moving objects for dynamic machine vision.

Multilevel resistive switching in stable all-inorganic n-i-p double perovskite memristor

Memristors are promising information storage devices for commercial applications because of their long endurance and low power consumption. Particularly, perovskite memristors have revealed excellent resistive switching (RS) properties owing to the fast ion migration and solution fabrication process. Here, an n-i-p type double perovskite memristor with "ITO/SnO₂/Cs₂AgBiBr₆/NiO_x/Ag" architecture was developed and demonstrated to reveal three resistance states because of the p-n junction electric field coupled with ion migration. The devices exhibited reliable filamentary with an on/off ratio exceeding 50. The RS characteristics remained unchanged after 1000 s read and 300 switching cycles. The synaptic functions were examined through long-term depression and potentiation measurements. Significantly, the device still worked after one year to reveal long-term stability because of the all-inorganic layers. This work indicates a novel idea for designing a multistate memristor by utilizing the p-n junction unidirectional conductivity during the forward and reverse scanning.

Reviving the Dynamics of Attacked Reservoir Computers

Physically implemented neural networks are subject to external perturbations and internal variations. Existing works focus on the adversarial attacks but seldom consider attack on the network structure and the corresponding recovery method. Inspired by the biological neural compensation mechanism and the neuromodulation technique in clinical practice, we propose a novel framework of reviving attacked reservoir computers, consisting of several strategies direct at different types of attacks on structure by adjusting only a minor fraction of edges in the reservoir. Numerical experiments demonstrate the efficacy and broad applicability of the framework and reveal inspiring insights into the mechanisms. This work provides a vehicle to improve the robustness of reservoir computers and can be generalized to broader types of neural networks.

Bioinspired Artificial Motion Sensory System for Rotation Recognition and Rapid Self-Protection

As one of the most common synergies between the exteroceptors and proprioceptors, the synergy between visual and vestibule enables the human brain to judge the state of human motion, which is essential for motion recognition and human self-protection. Hence, in this work, an artificial motion sensory system (AMSS) based on artificial vestibule and visual is developed, which consists of a tribo-nanogenerator (TENG) as a vestibule that can sense rotation and synaptic transistor array as retina. The principle of temporal congruency has been successfully realized by multisensory input. In addition, pattern recognition results show that the accuracy of multisensory integration is more than 15% higher than that of single sensory. Moreover, due to the rotation recognition and visual recognition functions of AMSS, we realized multimodal information recognition including angles and numbers in the spiking correlated neural network (SCNN), and the accuracy rate reached 89.82%. Besides, the rapid self-protection of a human was successfully realized by AMSS in the case of simulated amusement rides, and the reaction time of multiple motion sensory integration is only one-third of that of a single vestibule. The development of AMSS based on the synergy of simulated vision and vestibule will show great potential in neural robot, artificial limbs, and soft electronics.

Programmable ferroelectric bionic vision hardware with selective attention for high-precision image classification

Selective attention is an efficient processing strategy to allocate computational resources for pivotal optical information. However, the hardware implementation of selective visual attention in conventional intelligent system is usually bulky and complex along with high computational cost. Here, programmable ferroelectric bionic vision hardware to emulate the selective attention is proposed. The tunneling effect of photogenerated carriers are controlled by dynamic variation of energy barrier, enabling the modulation of memory strength from 9.1% to 47.1% without peripheral storage unit. The molecular polarization of ferroelectric P(VDF-TrFE) layer enables a single device not only multiple nonvolatile states but also the implementation of selective attention. With these ferroelectric devices are arrayed together, UV light information can be selectively recorded and suppressed the with high current decibel level. Furthermore, the device with positive polarization exhibits high wavelength dependence in the image attention processing, and the fabricated ferroelectric sensory network exhibits high accuracy of 95.7% in the pattern classification for multi-wavelength images. This study can enrich the neuromorphic functions of bioinspired sensing devices and pave the way for profound implications of future bioinspired optoelectronics.