Search

The rapid advancement of AI and machine learning has significantly enhanced sound and acoustic recognition technologies, moving beyond traditional models to more sophisticated neural network-based methods. Among these, Spiking Neural Networks (SNNs) are particularly noteworthy. SNNs mimic biological neurons and operate on principles similar to the human brain, using analog computing mechanisms. This capability allows for efficient sound processing with low power consumption and minimal latency, ideal for real-time applications in embedded systems. This paper reviews recent developments in SNNs for sound recognition, underscoring their potential to overcome the limitations of digital computing and suggesting directions for future research. The unique attributes of SNNs could lead to breakthroughs in mimicking human auditory processing more closely. [ABSTRACT FROM AUTHOR]

Abstract With remarkable electrical and optical switching properties induced at low power and near room temperature (68 °C), vanadium dioxide (VO2) has sparked rising interest in unconventional computing among the phase-change materials research community. The scalability and the potential to compute beyond the von Neumann model make VO2 especially appealing for implementation in oscillating neural networks for artificial intelligence applications, to solve constraint satisfaction problems, and for pattern recognition. Its integration into large networks of oscillators on a Silicon platform still poses challenges associated with the stabilization in the correct oxidation state and the ability to fabricate a structure with predictable electrical behavior showing very low variability. In this work, the role played by the different annealing parameters applied by three methods (slow thermal annealing, flash annealing, and rapid thermal annealing), following the vanadium oxide atomic layer deposition, on the formation of VO2 grains is studied and an optimal substrate stack configuration that minimizes variability between devices is proposed. Material and electrical characterizations are performed on the different films and a step-by-step recipe to build reproducible VO2-based oscillators is presented, which is argued to be made possible thanks to the introduction of a hafnium oxide (HfO2) layer between the silicon substrate and the vanadium oxide layer. Up to seven nearly identical VO2-based devices are contacted simultaneously to create a network of oscillators, paving the way for large-scale implementation of VO2 oscillating neural networks.

With remarkable electrical and optical switching properties induced at low power and near room temperature (68 °C), vanadium dioxide (VO2) has sparked rising interest in unconventional computing among the phase-change materials research community. The scalability and the potential to compute beyond the von Neumann model make VO2 especially appealing for implementation in oscillating neural networks for artificial intelligence applications, to solve constraint satisfaction problems, and for pattern recognition. Its integration into large networks of oscillators on a Silicon platform still poses challenges associated with the stabilization in the correct oxidation state and the ability to fabricate a structure with predictable electrical behavior showing very low variability. In this work, the role played by the different annealing parameters applied by three methods (slow thermal annealing, flash annealing, and rapid thermal annealing), following the vanadium oxide atomic layer deposition, on the formation of VO2 grains is studied and an optimal substrate stack configuration that minimizes variability between devices is proposed. Material and electrical characterizations are performed on the different films and a step-by-step recipe to build reproducible VO2-based oscillators is presented, which is argued to be made possible thanks to the introduction of a hafnium oxide (HfO2) layer between the silicon substrate and the vanadium oxide layer. Up to seven nearly identical VO2-based devices are contacted simultaneously to create a network of oscillators, paving the way for large-scale implementation of VO2 oscillating neural networks. [ABSTRACT FROM AUTHOR]

Neuromorphic engineering/computing addresses key challenges that modern electronics is facing such as high power consumption and high computing cost. Neuromorphic circuits for neurons and synapses will become key components to enable future neuromorphic computing system. Taking haptics for an example, in physical world, human haptic system is used to establish tactile sensation and feedback between human skin and physical objects. In Metaverse, computer haptics is used to build tactile sensation and haptic rendering when interacting with a virtual object and leads to an emerging technological field. This topic will be of great interest to thin film technology community and others to foster a discussion on possibility of using thin film devices to design such circuits for flexible and large area neuromorphic system. Author Keywords [ABSTRACT FROM AUTHOR]

Investigations in the field of spiking neural networks (SNNs) encompass diverse, yet overlapping, scientific disciplines. Examples range from purely neuroscientific investigations, researches on computational aspects of neuroscience, or applicative-oriented studies aiming to improve SNNs performance or to develop artificial hardware counterparts. However, the simulation of SNNs is a complex task that can not be adequately addressed with a single platform applicable to all scenarios. The optimization of a simulation environment to meet specific metrics often entails compromises in other aspects. This computational challenge has led to an apparent dichotomy of approaches, with model-driven algorithms dedicated to the detailed simulation of biological networks, and data-driven algorithms designed for efficient processing of large input datasets. Nevertheless, material scientists, device physicists, and neuromorphic engineers who develop new technologies for spiking neuromorphic hardware solutions would find benefit in a simulation environment that borrows aspects from both approaches, thus facilitating modeling, analysis, and training of prospective SNN systems. This manuscript explores the numerical challenges deriving from the simulation of spiking neural networks, and introduces SHIP, Spiking (neural network) Hardware In PyTorch, a numerical tool that supports the investigation and/or validation of materials, devices, small circuit blocks within SNN architectures. SHIP facilitates the algorithmic definition of the models for the components of a network, the monitoring of states and output of the modeled systems, and the training of the synaptic weights of the network, by way of user-defined unsupervised learning rules or supervised training techniques derived from conventional machine learning. SHIP offers a valuable tool for researchers and developers in the field of hardware-based spiking neural networks, enabling efficient simulation and validation of novel technologies. [ABSTRACT FROM AUTHOR]

Neuromorphic computing is an emerging research field that aims to develop new intelligent systems by integrating theories and technologies from multiple disciplines, such as neuroscience, deep learning and microelectronics. Various software frameworks have been developed for related fields, but an efficient framework dedicated to spike-based computing models and algorithms is lacking. In this work, we present a Python-based spiking neural network (SNN) simulation and training framework, named SPAIC, that aims to support brain-inspired model and algorithm research integrated with features from both deep learning and neuroscience. To integrate different methodologies from multiple disciplines and balance flexibility and efficiency, SPAIC is designed with a neuroscience-style frontend and a deep learning-based backend. Various types of examples are provided to demonstrate the wide usability of the framework, including neural circuit simulation, deep SNN learning and neuromorphic applications. As a user-friendly, flexible, and high-performance software tool, it will help accelerate the rapid growth and wide applicability of neuromorphic computing methodologies. [ABSTRACT FROM AUTHOR]

In this paper, we propose a compact and low-power mixed-signal approach to implementing convolutional operators that are often responsible for most of the chip area and power consumption of Convolutional Neural Network (CNN) processing chips. The convolutional operators consist of several multiply-and-accumulate (MAC) units. MAC units are the primary components that process convolutional layers and fully connected layers of CNN models. Analog implementation of MAC units opens a new paradigm for realizing low-power CNN processing chips, benefiting from less power and area consumption. The proposed mixed-signal convolutional operator comprises low-power binary-weighted current steering digital-to-analog conversion (DAC) circuits and accumulation capacitors. Compared with a conventional binary-weighted DAC, the proposed circuit benefits from optimum accuracy, smaller area, and lower power consumption due to its symmetric design. The proposed convolutional operator takes as input a set of 9-bit digital input feature data and weight parameters of the convolutional filter. It then calculates the convolutional filter's result and accumulates the resulting voltage on capacitors. In addition, the convolutional operator employs a novel charge-sharing technique to process negative MAC results. We propose an analog max-pooling circuit that instantly selects the maximum input voltage. To demonstrate the performance of the proposed mixed-signal convolutional operator, we implemented a CNN processing chip consisting of 3 analog convolutional operators, with each operator processing a 3 × 3 kernel. This chip contains 27 MAC circuits, an analog max-pooling, and an analog-to-digital conversion (ADC) circuit. The mixed-signal CNN processing chip is implemented using a CMOS 55 nm process, which occupies a silicon area of 0.0559 mm2 and consumes an average power of 540.6 μW. The proposed mixed-signal CNN processing chip offers an area reduction of 84.21% and an energy reduction of 91.85% compared with a conventional digital CNN processing chip. Moreover, another CNN processing chip is implemented with more analog convolutional operators to demonstrate the operation and structure of an example convolutional layer of a CNN model. Therefore, the proposed analog convolutional operator can be adapted in various CNN models as an alternative to digital counterparts. [ABSTRACT FROM AUTHOR]

One of the emerging paradigms to resolve pressing issues of modern computing electronics, such as limits in miniaturization and excessive energy consumption, takes inspiration from the biological brain and is therefore expected to display some of its properties, such as energy efficiency and effective learning. Moreover, one of the brain's remarkable properties is its ability to process complex information by resolving it on different timescales. In synapse‐emulating artificial devices, some form of memory (e.g., hysteresis in current–voltage characteristics) is required. One of the important characteristics of biological synapses is the coexistence of short‐ and long‐term memory, also called plasticity. However, a broader exploration of memory at multiple timescales in materials remains limited. Herein, the first example of synaptic transistors utilizing colloidal quantum dots (CQDs) as active material is reported. It is demonstrated that PbS‐CQDs, with metal halide and perovskite‐like ligands, are ideal as an active material for synaptic transistors exhibiting both short‐ and long‐term plasticity. Most interestingly, by changing the chemistry of the quantum dot outer monolayer, a drastic change in the temporal response of the learning is observed, demonstrating the possibility of engineering materials exhibiting learning at multiple timescales, similar to the biological synapses. [ABSTRACT FROM AUTHOR]

The brain has great capacity for computation and efficient resolution of complex problems, far surpassing modern computers. Neuromorphic engineering seeks to mimic the basic principles of the brain to develop systems capable of achieving such capabilities. In the neuromorphic field, navigation systems are of great interest due to their potential applicability to robotics, although these systems are still a challenge to be solved. This work proposes a spike‐based robotic navigation and environment pseudomapping system formed by a bioinspired hippocampal memory model connected to a posterior parietal cortex (PPC) model. The hippocampus is in charge of maintaining a representation of an environment state map, and the PPC is in charge of local decision‐making. This system is implemented on the SpiNNaker hardware platform using spiking neural networks. A set of real‐time experiments are applied to demonstrate the correct functioning of the system in virtual and physical environments on a robotic platform. The system is able to navigate through the environment to reach a goal position starting from an initial position, avoiding obstacles and mapping the environment. To the best of the authors' knowledge, this is the first implementation of an environment pseudomapping system with dynamic learning based on a bioinspired hippocampal memory. [ABSTRACT FROM AUTHOR]

In deep neural networks, representational learning in the middle layer is essential for achieving efficient learning. However, the currently prevailing backpropagation learning rules (BP) are not necessarily biologically plausible and cannot be implemented in the brain in their current form. Therefore, to elucidate the learning rules used by the brain, it is critical to establish biologically plausible learning rules for practical memory tasks. For example, learning rules that result in a learning performance worse than that of animals observed in experimental studies may not be computations used in real brains and should be ruled out. Using numerical simulations, we developed biologically plausible learning rules to solve a task that replicates a laboratory experiment where mice learned to predict the correct reward amount. Although the extreme learning machine (ELM) and weight perturbation (WP) learning rules performed worse than the mice, the feedback alignment (FA) rule achieved a performance equal to that of BP To obtain a more biologically plausible model, we developed a variant of FA, FA_Ex-100%, which implements direct dopamine inputs that provide error signals locally in the layer of focus, as found in the mouse entorhinal cortex. The performance of FA_Ex-100% was comparable to that of conventional BP Finally, we tested whether FA_Ex-100% was robust against rule perturbations and biologically inevitable noise. FA_Ex-100% worked even when subjected to perturbations, presumably because it could calibrate the correct prediction error (e.g., dopaminergic signals) in the next step as a teaching signal if the perturbation created a deviation. These results suggest that simplified and biologically plausible learning rules, such as FA_Ex-100%, can robustly facilitate deep supervised learning when the error signal, possibly conveyed by dopaminergic neurons, is accurate. [ABSTRACT FROM AUTHOR]

Memristors possess non-volatile memory, adjusting their electrical resistance to the current that flows through them and allowing switching between high and low conducting states. This technology could find applications in fields such as IT, consumer electronics, computing, sensors, and medicine. In this paper, we report successful electrodeposition of thin-film materials consisting of copper tungstate and copper molybdate (CuWO4 and Cu3Mo2O9), which showed notable memristive properties. Material characterisation was performed with techniques such as XRD, XPS, and SEM. The electrodeposited materials exhibited the ability to switch between low and high resistive states during varied cyclic scans and short-term impulses. The retention time of these switched states was also explored. Using these materials, the effects seen in biological systems, specifically spike timing-dependent plasticity, were simulated, being based on analogue operation of the memristors to achieve multiple conductivity states. Bio-inspired simulations performed directly on the material could possibly offer energy and time savings for classical computations. Memristors could be crucial for the advancement of high-efficiency, low-energy neuromorphic electronic devices and technologies in the future. [ABSTRACT FROM AUTHOR]

Reservoir computing (RC) is a neural computing paradigm especially well-suited for learning dynamical systems by leveraging an untrained reservoir layer, providing high-dimensional input encoding with fading memory property. Since only the readout weights are trained under RC, linear regression learning algorithms are sufficient, leading to significant improvements in computational complexity and energy efficiency as compared to other deep neural networks (DNNs). RC offers an alternative solution to sidestep the shortcomings of data scarcity and the vanishing gradient problem. More importantly, such a network structure is amenable to hardware implementation using a variety of devices, circuits, and systems, making RC a good candidate to replace sophisticated DNNs as a lightweight classifier at the edge for internet of things (IoT) applications. In this article, we provide an overview of recent advances in RC hardware and their applications for mobile edge intelligence. Specifically, we will demonstrate the design strategies of RC in opto-electronic configuration, fully digital system, and silicon with the mixed-signal integrated circuit approach. Moreover, we will expose a novel implementation approach using emerging materials, designing the way for RC to be used in the next-generation neuromorphic computing systems. Building upon these efficient RC models, their applicability and effectiveness against the state-of-the-art are then demonstrated through diverse machine learning benchmarks spanning the area of IoT, communication networks, and healthcare. [ABSTRACT FROM AUTHOR]

Muscles are stretched with bursts of spikes that come from motor neurons connected to the cerebellum through the spinal cord. Then, alpha motor neurons directly innervate the muscles to complete the motor command coming from upper biological structures. Nevertheless, classical robotic systems usually require complex computational capabilities and relative high-power consumption to process their control algorithm, which requires information from the robot's proprioceptive sensors. The way in which the information is encoded and transmitted is an important difference between biological systems and robotic machines. Neuromorphic engineering mimics these behaviors found in biology into engineering solutions to produce more efficient systems and for a better understanding of neural systems. This paper presents the application of a Spike-based Proportional-Integral-Derivative controller to a 6-DoF Scorbot ER-VII robotic arm, feeding the motors with Pulse-Frequency-Modulation instead of Pulse-Width-Modulation, mimicking the way in which motor neurons act over muscles. The presented frameworks allow the robot to be commanded and monitored locally or remotely from both a Python software running on a computer or from a spike-based neuromorphic hardware. Multi-FPGA and single-PSoC solutions are compared. These frameworks are intended for experimental use of the neuromorphic community as a testbed platform and for dataset recording for machine learning purposes. [ABSTRACT FROM AUTHOR]

This paper introduces Tensor-Organized Memory (TOM), a novel neuromorphic architecture inspired by the human brain's structural and functional principles. Utilizing spike-timing-dependent plasticity (STDP) and Hebbian rules, TOM exhibits cognitive behaviors similar to the human brain. Compared to conventional architectures using a simplified leaky integrate-and-fire (LIF) neuron model, TOM showcases robust performance, even in noisy conditions. TOM's adaptability and unique organizational structure, rooted in the Columnar-Organized Memory (COM) framework, position it as a transformative digital memory processing solution. Innovative neural architecture, advanced recognition mechanisms, and integration of synaptic plasticity rules enhance TOM's cognitive capabilities. We have compared the TOM architecture with a conventional floating-point architecture, using a simplified LIF neuron model. We also implemented tests with varying noise levels and partially erased messages to evaluate its robustness. Despite the slight degradation in performance with noisy messages beyond 30%, the TOM architecture exhibited appreciable performance under less-than-ideal conditions. This exploration into the TOM architecture reveals its potential as a framework for future neuromorphic systems. This study lays the groundwork for future applications in implementing neuromorphic chips for high-performance intelligent edge devices, thereby revolutionizing industries and enhancing user experiences within the power of artificial intelligence. [ABSTRACT FROM AUTHOR]

Humanity is spurred to tackle multi-sectorial global challenges involving everyone on Earth. Global challenges require global agendas to be faced. Global plans focus on the management of Complex Systems. Therefore, the development of Complexity Science is urgent. This contribution outlines the investigation of Complex Systems from an ontological and epistemological point of view. It highlights the relevant role of Natural Computing in facing the description, prediction, and more in-depth comprehension of Complex Systems. Its rationale constitutes an interpretative key for describing and understanding the behaviour of Complex Systems. Furthermore, developing new algorithms and possibly new computing machines will allow humanity to tackle Epistemological Complexity more effectively. Among all the possible sources of inspiration, human intelligence is undoubtedly the most in vogue. This work reveals that the imitation of human intelligence and the consequent development of Artificial Intelligence can be carried out not only through traditional strategies but also through Molecular, Supramolecular, and Systems Chemistries. Chemical Artificial Intelligence promises to contribute to understanding the ontology of Complex Systems and facing epistemological Complexity. [ABSTRACT FROM AUTHOR]

One of the emerging paradigms to resolve pressing issues of modern computing electronics, such as limits in miniaturization and excessive energy consumption, takes inspiration from the biological brain and is therefore expected to display some of its properties, such as energy efficiency and effective learning. Moreover, one of the brain's remarkable properties is its ability to process complex information by resolving it on different timescales. In synapse‐emulating artificial devices, some form of memory (e.g., hysteresis in current–voltage characteristics) is required. One of the important characteristics of biological synapses is the coexistence of short‐ and long‐term memory, also called plasticity. However, a broader exploration of memory at multiple timescales in materials remains limited. Herein, the first example of synaptic transistors utilizing colloidal quantum dots (CQDs) as active material is reported. It is demonstrated that PbS‐CQDs, with metal halide and perovskite‐like ligands, are ideal as an active material for synaptic transistors exhibiting both short‐ and long‐term plasticity. Most interestingly, by changing the chemistry of the quantum dot outer monolayer, a drastic change in the temporal response of the learning is observed, demonstrating the possibility of engineering materials exhibiting learning at multiple timescales, similar to the biological synapses.

The brain has great capacity for computation and efficient resolution of complex problems, far surpassing modern computers. Neuromorphic engineering seeks to mimic the basic principles of the brain to develop systems capable of achieving such capabilities. In the neuromorphic field, navigation systems are of great interest due to their potential applicability to robotics, although these systems are still a challenge to be solved. This work proposes a spike‐based robotic navigation and environment pseudomapping system formed by a bioinspired hippocampal memory model connected to a posterior parietal cortex (PPC) model. The hippocampus is in charge of maintaining a representation of an environment state map, and the PPC is in charge of local decision‐making. This system is implemented on the SpiNNaker hardware platform using spiking neural networks. A set of real‐time experiments are applied to demonstrate the correct functioning of the system in virtual and physical environments on a robotic platform. The system is able to navigate through the environment to reach a goal position starting from an initial position, avoiding obstacles and mapping the environment. To the best of the authors’ knowledge, this is the first implementation of an environment pseudomapping system with dynamic learning based on a bioinspired hippocampal memory.

Spike-based perception brings up a new research idea in the field of neuromorphic engineering. A high-performance biologically inspired flexible spiking neural network (SNN) architecture provides a novel method for the exploration of perception mechanisms and the development of neuromorphic computing systems. In this article, we present a biological-inspired spike-based SNN perception digital system that can realize robust perception. The system employs a fully paralleled pipeline scheme to improve the performance and accelerate the processing of feature extraction. An auditory perception system prototype is realized on ten Intel Cyclone field-programmable gate arrays, which can reach the maximum frequency of 107.28 MHz and the maximum throughput of 5364 Mbps. Our design also achieves the power of 5. 148 W/system and energy efficiency of 845.85 μ J. Our auditory perception implementation is also proved to have superior robustness compared with other SNN systems. We use TIMIT digit speech in noise in accuracy testing. Result shows that it achieves up to 85.75% speech recognition accuracy under obvious noise conditions (signal-to-noise ratio of 20 dB) and maintain small accuracy attenuation with the decline of the signal-to-noise ratio. The overall performance of our proposed system outperforms the state-of-the-art perception system on SNN. [ABSTRACT FROM AUTHOR]

The potential role of bottom-up Synthetic Cells (SCs) in the Internet of Bio-Nano Things (IoBNT) is discussed. In particular, this perspective paper focuses on the growing interest in networks of biological and/or artificial objects at the micro- and nanoscale (cells and subcellular parts, microelectrodes, microvessels, etc.), whereby communication takes place in an unconventional manner, i.e., via chemical signaling. The resulting "molecular communication" (MC) scenario paves the way to the development of innovative technologies that have the potential to impact biotechnology, nanomedicine, and related fields. The scenario that relies on the interconnection of natural and artificial entities is briefly introduced, highlighting how Synthetic Biology (SB) plays a central role. SB allows the construction of various types of SCs that can be designed, tailored, and programmed according to specific predefined requirements. In particular, "bottom-up" SCs are briefly described by commenting on the principles of their design and fabrication and their features (in particular, the capacity to exchange chemicals with other SCs or with natural biological cells). Although bottom-up SCs still have low complexity and thus basic functionalities, here, we introduce their potential role in the IoBNT. This perspective paper aims to stimulate interest in and discussion on the presented topics. The article also includes commentaries on MC, semantic information, minimal cognition, wetware neuromorphic engineering, and chemical social robotics, with the specific potential they can bring to the IoBNT. [ABSTRACT FROM AUTHOR]

This work highlights the utilization of the floating body effect and charge-trapping/de-trapping phenomenon of a Silicon-nanowire (Si-nanowire) charge-trapping memory for an artificial synapse of neuromorphic computing application. Charge trapping/de-trapping in the nitride layer characterizes the long-term potentiation (LTP)/depression (LTD). The accumulation of holes in the potential well achieves short-term potentiation (STP) and controls the transition from STP to LTP. Also, the transition from STP to LTP is analyzed through gate length scaling and high-κ material (Al2O3) for blocking oxide. Furthermore, the conductance values of the device are utilized for system-level simulation. System-level hardware parameters of a convolutional neural network (CNN) for inference applications are evaluated and compared to a static random-access memory (SRAM) device and charge-trapping memory. The results confirm that the Si-nanowire transistor with better gate controllability has a high retention time for LTP states, consumes low power, and archives better accuracy (91.27%). These results make the device suitable for low-power neuromorphic applications. [ABSTRACT FROM AUTHOR]

The essential step for developing neuromorphic systems is to construct more biorealistic elementary devices with rich spatiotemporal dynamics to exhibit highly separable responses in dynamic environmental circumstances. Unlike transistor‐based devices and circuits with zeroth‐order complexity, memristors intrinsically express some simple biomimetic functions. However, with only two‐terminal structure, precise control of operation principles to ensure large dynamic space, improved linearity and symmetry, multimodal operation as well as high‐order complexity is hard to achieve in a traditional memristor owing to its limited degree of freedom. Therefore, multiterminal memristors including both concrete terminals and virtual terminals (light, pressure, gas, ferroelectric polarity, etc.) have been proposed to obtain precise modulation of memristive characteristics. This review focuses on the recent progress in multiterminal memristors and their neuromorphic applications. The operation principle, application of multiterminal memristor on neuromorphic computing in different scenarios, existing challenges and future prospects are discussed. [ABSTRACT FROM AUTHOR]

Lithium (Li)-ion materials such as LiCoO2 and (Li3PO4)-N (LiPON) are used in Li-ion all-solid-state batteries, and are now expected to be used as ion-electron hybrid materials to create a new degree of freedom in future integrated circuits. We fabricated thin-film devices on the basis of LiCoO2/LiPON/Cu and ultrathin titanium oxide ( ${\mathrm {TiO}}_{x}$ ) to demonstrate their new type of resistance change mechanism and characteristics. Multi-level resistance changes promising as synaptic plasticity were obtained, and the resistance properties enable neuromorphic computing to enter a new era.

This paper presents a reconfigurable digital implementation of an event-based binaural cochlear system on a Field Programmable Gate Array (FPGA). It consists of a pair of the Cascade of Asymmetric Resonators with Fast Acting Compression (CAR-FAC) cochlea models and leaky integrate-and-fire (LIF) neurons. Additionally, we propose an event-driven SpectroTemporal Receptive Field (STRF) Feature Extraction using Adaptive Selection Thresholds (FEAST). It is tested on the TIDIGTIS benchmark and compared with current event-based auditory signal processing approaches and neural networks. [ABSTRACT FROM AUTHOR]

With the increasing demands on unstructured data processing, a system emulating the human nervous system has garnered great attention as an alternative to the von-Neumann architecture due to low power consumption and parallel data processing. To realize the neuromorphic computing, the artificial electronic synapse, neuron device and architecture have been investigated using various materials and devices. In this regard, in addition to electrical-responsive synaptic devices, photoresponsive synapse devices are attracting attention due to photoresponse with high bandwidth, low power consumption, and low current crosstalk. Espicially, the organic-inorganic hybrid halide perovskites (OIHPs) are promising materials for photodevices due to broad optical absorption, low exciton binding energy, fast charge transport properties, and tunable bandgap. The OIHPs have been implemented to demonstrate the photo-stimulated synaptic functions, however, most OIHPs contain toxic lead cations, limiting their widespread application. In this study, we investigated the light-stimulated photosynaptic characteristics based on OIHPs synthesized with Mn2+ (CH 3 NH 3 Pb 1-x Mn x Br 2x+1) that could substitute non-desirable Pb-based perovskite. The Mn2+-based OIHPs photosynapstor successfully emulated the essential synaptic characteristics including excitatory post-synaptic current, pulse-paired facilitation, post-tetanic potentiation, transition from short-term plasticity to long-term plasticity, forgetting curve, and spike-timing dependent plasticity. [ABSTRACT FROM AUTHOR]

Neuromorphic computation processes sensors output in the spiking domain, which presents constraints in many cases when converting information to spikes, loosing, as example, temporal accuracy. This paper presents a spike-based system to adapt audio information from low-power pulse-density modulation (PDM) microelectromechanical systems microphones into rate coded spike frequencies. These spikes could be directly used by the neuromorphic auditory sensor (NAS) for frequency decomposition in different bands, avoiding the analog or digital conversion to spike streams. This improves the time response of the NAS, allowing its use in more time restrictive applications. This adaptation was conducted in VHDL as an interface for PDM microphones, converting their pulses into temporal distributed spikes following a pulse-frequency modulation scheme with an accurate inter-spike-interval, known as PDM to spikes interface (PSI). We introduce a new architecture of spike-based band-pass filter to reject DC components and distribute spikes in time. This was tested in two scenarios, first as a stand-alone circuit for its characterization, and then integrated with a NAS for verification. The PSI achieves a total harmonic distortion of - 46.18 dB and a signal-to-noise ratio of 63.47 dB, demands less than 1% of the resources of a Spartan-6 FPGA and its power consumption is around 7 mW. [ABSTRACT FROM AUTHOR]

Abstract The essential step for developing neuromorphic systems is to construct more biorealistic elementary devices with rich spatiotemporal dynamics to exhibit highly separable responses in dynamic environmental circumstances. Unlike transistor‐based devices and circuits with zeroth‐order complexity, memristors intrinsically express some simple biomimetic functions. However, with only two‐terminal structure, precise control of operation principles to ensure large dynamic space, improved linearity and symmetry, multimodal operation as well as high‐order complexity is hard to achieve in a traditional memristor owing to its limited degree of freedom. Therefore, multiterminal memristors including both concrete terminals and virtual terminals (light, pressure, gas, ferroelectric polarity, etc.) have been proposed to obtain precise modulation of memristive characteristics. This review focuses on the recent progress in multiterminal memristors and their neuromorphic applications. The operation principle, application of multiterminal memristor on neuromorphic computing in different scenarios, existing challenges and future prospects are discussed.

A neuromorphic simultaneous localization and mapping (SLAM) system shows potential for more efficient implementation than its traditional counterpart. At the mean time a neuromorphic model of spatial encoding neurons in silicon could provide insights on the functionality and dynamic between each group of cells. Especially when realistic factors including variations and imperfections on the neural movement encoding are presented to challenge the existing hypothetical models for localization. We demonstrate a mixed-mode implementation for spatial encoding neurons including theta cells, egocentric place cells, and the typical allocentric place cells. Together, they form a biologically plausible network that could reproduce the localization functionality of place cells observed in rodents. The system consists of a theta chip with 128 theta cell units and an FPGA implementing 4 networks for egocentric place cells formation that provides the capability for tracking on a 11 by 11 place cell grid. Experimental results validate the robustness of our model when suffering from as much as 18% deviation, induced by parameter variations in analog circuits, from the mathematical model of theta cells. We provide a model for implementing dynamic neuromorphic SLAM systems for dynamic-scale mapping of cluttered environments, even when subject to significant errors in sensory measurements and real-time analog computation. We also suggest a robust approach for the network topology of spatial cells that can mitigate neural non-uniformity and provides a hypothesis for the function of grid cells and the existence of egocentric place cells.

With the remarkable progress that technology has made, the need for processing data near the sensors at the edge has increased dramatically. The electronic systems used in these applications must process data continuously, in real-time, and extract relevant information using the smallest possible energy budgets. A promising approach for implementing always-on processing of sensory signals that supports on-demand, sparse, and edge-computing is to take inspiration from biological nervous system. Following this approach, we present a brain-inspired platform for prototyping real-time event-based spiking neural networks. The system proposed supports the direct emulation of dynamic and realistic neural processing phenomena such as short-term plasticity, NMDA gating, AMPA diffusion, homeostasis, spike frequency adaptation, conductance-based dendritic compartments and spike transmission delays. The analog circuits that implement such primitives are paired with a low latency asynchronous digital circuits for routing and mapping events. This asynchronous infrastructure enables the definition of different network architectures, and provides direct event-based interfaces to convert and encode data from event-based and continuous-signal sensors. Here we describe the overall system architecture, we characterize the mixed signal analog-digital circuits that emulate neural dynamics, demonstrate their features with experimental measurements, and present a low- and high-level software ecosystem that can be used for configuring the system. The flexibility to emulate different biologically plausible neural networks, and the chip’s ability to monitor both population and single neuron signals in real-time, allow to develop and validate complex models of neural processing for both basic research and edge-computing applications.

In this paper, we propose a compact and low-power mixed-signal approach to implementing convolutional operators that are often responsible for most of the chip area and power consumption of Convolutional Neural Network (CNN) processing chips. The convolutional operators consist of several multiply-and-accumulate (MAC) units. MAC units are the primary components that process convolutional layers and fully connected layers of CNN models. Analog implementation of MAC units opens a new paradigm for realizing low-power CNN processing chips, benefiting from less power and area consumption. The proposed mixed-signal convolutional operator comprises low-power binary-weighted current steering digital-to-analog conversion (DAC) circuits and accumulation capacitors. Compared with a conventional binary-weighted DAC, the proposed circuit benefits from optimum accuracy, smaller area, and lower power consumption due to its symmetric design. The proposed convolutional operator takes as input a set of 9-bit digital input feature data and weight parameters of the convolutional filter. It then calculates the convolutional filter’s result and accumulates the resulting voltage on capacitors. In addition, the convolutional operator employs a novel charge-sharing technique to process negative MAC results. We propose an analog max-pooling circuit that instantly selects the maximum input voltage. To demonstrate the performance of the proposed mixed-signal convolutional operator, we implemented a CNN processing chip consisting of 3 analog convolutional operators, with each operator processing a 3 × 3 kernel. This chip contains 27 MAC circuits, an analog max-pooling, and an analog-to-digital conversion (ADC) circuit. The mixed-signal CNN processing chip is implemented using a CMOS 55 nm process, which occupies a silicon area of 0.0559 mm2 and consumes an average power of 540.6 μW. The proposed mixed-signal CNN processing chip offers an area reduction of 84.21% and an energy reduction of 91.85% compared with a conventional digital CNN processing chip. Moreover, another CNN processing chip is implemented with more analog convolutional operators to demonstrate the operation and structure of an example convolutional layer of a CNN model. Therefore, the proposed analog convolutional operator can be adapted in various CNN models as an alternative to digital counterparts.

The neuromorphic engineering field aims to mimic complex biological structures by means of mathematical models, implementing them in either analog or digital circuits. These models include the dynamic characteristics of biological neurons and synapses, which are interconnected creating spiking neural networks. These are first simulated using software frameworks in order to verify the expected behavior of the implemented model. In this work, a novel software, called NESIM-RT, for simulating spiking neural networks in real time is presented. A friendly user interface allows users to design and modify the network, together with visualising its output in real time. A novel implementation of the MDHCP protocol is proposed to support online changes in the network together with allowing the simulation in a many-cores distributed architecture. The performance of the proposed software is compared with other widely-used simulators in the neuromorphic engineering field, highlighting the advantages in terms of latencies and network scalability. NESIM-RT also allows exporting the SNN model directly to SpiNNaker, enabling an immediate transition between software simulation and hardware implementation.

Introduction: Spiking Neural Networks (SNNs) are gaining significant traction in machine learning tasks where energy-efficiency is of utmost importance. Training such networks using the state-of-the-art back-propagation through time (BPTT) is, however, very time-consuming. Previous work employs an efficient GPU-accelerated backpropagation algorithm called SLAYER, which speeds up training considerably. SLAYER, however, does not take into account the neuron reset mechanism while computing the gradients, which we argue to be the source of numerical instability. To counteract this, SLAYER introduces a gradient scale hyper parameter across layers, which needs manual tuning. Methods: In this paper, we modify SLAYER and design an algorithm called EXODUS, that accounts for the neuron reset mechanism and applies the Implicit Function Theorem (IFT) to calculate the correct gradients (equivalent to those computed by BPTT). We furthermore eliminate the need for ad-hoc scaling of gradients, thus, reducing the training complexity tremendously. Results: We demonstrate, via computer simulations, that EXODUS is numerically stable and achieves comparable or better performance than SLAYER especially in various tasks with SNNs that rely on temporal features. [ABSTRACT FROM AUTHOR]

Why do neurons communicate through spikes? By definition, spikes are all-or-none neural events which occur at continuous times. In other words, spikes are on one side binary, existing or not without further details, and on the other, can occur at any asynchronous time, without the need for a centralized clock. This stands in stark contrast to the analog representation of values and the discretized timing classically used in digital processing and at the base of modern-day neural networks. As neural systems almost systematically use this so-called event-based representation in the living world, a better understanding of this phenomenon remains a fundamental challenge in neurobiology in order to better interpret the profusion of recorded data. With the growing need for intelligent embedded systems, it also emerges as a new computing paradigm to enable the efficient operation of a new class of sensors and event-based computers, called neuromorphic, which could enable significant gains in computation time and energy consumption—a major societal issue in the era of the digital economy and global warming. In this review paper, we provide evidence from biology, theory and engineering that the precise timing of spikes plays a crucial role in our understanding of the efficiency of neural networks. [ABSTRACT FROM AUTHOR]

Event-based dynamic vision sensors provide very sparse output in the form of spikes, which makes them suitable for low-power applications. Convolutional spiking neural networks model such event-based data and develop their full energy-saving potential when deployed on asynchronous neuromorphic hardware. Event-based vision being a nascent field, the sensitivity of spiking neural networks to potentially malicious adversarial attacks has received little attention so far. We show how white-box adversarial attack algorithms can be adapted to the discrete and sparse nature of event-based visual data, and demonstrate smaller perturbation magnitudes at higher success rates than the current state-of-the-art algorithms. For the first time, we also verify the eectiveness of these perturbations directly on neuromorphic hardware. Finally, we discuss the properties of the resulting perturbations, the eect of adversarial training as a defense strategy, and future direction. [ABSTRACT FROM AUTHOR]

Linear weights modulation in neuromorphic memristor plays an important role in high-accuracy image recognition task. Herein, a Li+ doped organic artificial memristor for neuromorphic computing was proposed for linear weights update, which shows active ions diffusive dynamics as Ca2+ diffusion in biological synapse. The memristor exhibits gradual resistive switching, multi-state storage and typical synaptic behaviors. In addition, the synaptic learning capability of letter “T” was demonstrated in a memristors array. By designing consecutive pulse waveforms with enhanced amplitude, the linearity of memristor for weight update in long-term potentiation and depression (LTP/LTD) could be improved from 6.8 to 0.4. Based on the great nonlinearity factor in LTP ($\alpha _{\text {p}}={1.5}$) and LTD ($\alpha _{\text {d}}={0.4}$), face recognition was achieved with high accuracy of 96% by artificial neural network consisting of ion doped memristors. The ion doped organic memristor with highly linear weights update provides guidelines for the development of bio-inspired ion diffusive neuromorphic computing system. [ABSTRACT FROM AUTHOR]