Supervised learning in spiking neural networks: A review of algorithms and evaluations

Sign potential-driven multiplicative optimization for robust deep reinforcement learning

Deep Reinforcement Learning (DRL) has attracted the interest of researchers due to its ability to provide valuable solutions to a variety of problems in different fields, such as robotics, autonomous driving, financial trading, and more. However, DRL models are often sensitive and exhibit unstable behavior during both training and evaluation, increasing the interest in implementing robust methods to enhance the DRL training process. Taking into consideration that optimization methods based on multiplicative updates have shown to leverage advantages over additive ones in terms of convergence and robustness, we propose a novel momentum-based optimization approach that overcomes significant limitations of existing methods, such as the inability of multiplicative updates to flip the sign of parameters. More specifically, the proposed approach employs a sign-change mechanism, inspired by spiking neural networks, allowing parameters to change signs benefiting in that way the training process in terms of learning acceleration and robustness. The proposed optimizer is oriented to train DRL agents and is experimentally evaluated in various tasks, demonstrating its effectiveness in the training of DRL agents.

Unsupervised post-training learning in spiking neural networks

The human brain is a dynamic system that is constantly learning. It employs a combination of various learning strategies to facilitate complex learning processes. However, implementing biological learning mechanisms into Spiking Neural Networks (SNNs) remains challenging; thus, most SNNs are trained with only a single learning strategy such as spike timing dependent plasticity (STDP). Moreover, conventional neural networks are first trained on one dataset and subsequently evaluated on unseen data. In this traditional approach, the weights and structure of the model remain fixed once the training step concludes. In this research, we aim to modify this traditional approach and hypothesize that adding short-term plasticity (STP) to a trained SNN enables the model to learn post-training without changing synaptic weights. In particular, by combining triplet STDP for long-term learning during initial training and STP for short-term learning after training (post-training), we employ multiple learning rules to enhance the biological plausibility and computational abilities of SNNs. In this way, two unsupervised learning pipelines are designed for image classification as a proof of concept, in which the dynamic synapse model, driven by neurotransmitter release and synaptic strength, is integrated into the trained network. The proposed method outperforms traditional training by achieving higher classification accuracy and a faster convergence rate. Consequently, our results show that the concept of post-training learning can be realized by incorporating STP in SNNs. Future studies should extend this concept to other challenges and explore its applicability to new datasets.

Forced Oscillation Detection via a Hybrid Network of a Spiking Recurrent Neural Network and LSTM

The detection of forced oscillations, especially distinguishing them from natural oscillations, has emerged as a major concern in power system stability monitoring. Deep learning (DL) holds significant potential for detecting forced oscillations correctly. However, existing artificial neural networks (ANNs) face challenges when employed in edge devices for timely detection due to their inherent complex computations and high power consumption. This paper proposes a novel hybrid network that integrates a spiking recurrent neural network (SRNN) with long short-term memory (LSTM). The SRNN achieves computational and energy efficiency, while the integration with LSTM is conducive to effectively capturing temporal dependencies in time-series oscillation data. The proposed hybrid network is trained using the backpropagation-through-time (BPTT) optimization algorithm, with adjustments made to address the discontinuous gradient in the SRNN. We evaluate our proposed model on both simulated and real-world oscillation datasets. Overall, the experimental results demonstrate that the proposed model can achieve higher accuracy and superior performance in distinguishing forced oscillations from natural oscillations, even in the presence of strong noise, compared to pure LSTM and other SRNN-related models.

Spiking Neuron-Astrocyte Networks for Image Recognition

From biological and artificial network perspectives, researchers have started acknowledging astrocytes as computational units mediating neural processes. Here, we propose a novel biologically inspired neuron-astrocyte network model for image recognition, one of the first attempts at implementing astrocytes in spiking neuron networks (SNNs) using a standard data set. The architecture for image recognition has three primary units: the preprocessing unit for converting the image pixels into spiking patterns, the neuron-astrocyte network forming bipartite (neural connections) and tripartite synapses (neural and astrocytic connections), and the classifier unit. In the astrocyte-mediated SNNs, an astrocyte integrates neural signals following the simplified Postnov model. It then modulates the integrate-and-fire (IF) neurons via gliotransmission, thereby strengthening the synaptic connections of the neurons within the astrocytic territory. We develop an architecture derived from a baseline SNN model for unsupervised digit classification. The spiking neuron-astrocyte networks (SNANs) display better network performance with an optimal variance-bias trade-off than SNN alone. We demonstrate that astrocytes promote faster learning, support memory formation and recognition, and provide a simplified network architecture. Our proposed SNAN can serve as a benchmark for future researchers on astrocyte implementation in artificial networks, particularly in neuromorphic systems, for its simplified design.

Recent Advances in Surface-Enhanced Raman Scattering for Pathogenic Bacteria Detection: A Review

Bacterial infection is one of the common infectious diseases in clinical practice, and the research on efficient detection of bacteria has attracted much attention in recent years. Currently, the traditional detection methods of bacteria are mainly based on cell culturing, microscopic examination, and molecular biology techniques, all of which have the disadvantages of complex operation and time-consuming. Surface-enhanced Raman spectroscopy (SERS) technology has shown prominent advantages in bacterial detection and identification because of the merit of high-sensitivity, fast detection and unique molecular fingerprint spectrum. This paper mainly investigates and discusses the application of SERS in bacterial detection, and systematically reviews the progress of SERS applications, including nano-enhanced dielectric materials of SERS, signal amplification of SERS labeled molecules, and the integration of SERS with microfluidic technology. Finally, the paper analyzes the challenges associated with the application of SERS in bacterial detection and offers insights into future development trends.

Effective Surrogate Gradient Learning With High-Order Information Bottleneck for Spike-Based Machine Intelligence

Brain-inspired computing technique presents a promising approach to prompt the rapid development of artificial general intelligence (AGI). As one of the most critical aspects, spiking neural networks (SNNs) have demonstrated superiority for AGI, such as low power consumption. Effective training of SNNs with high generalization ability, high robustness, and low power consumption simultaneously is a significantly challenging problem for the development and success of applications of spike-based machine intelligence. In this research, we present a novel and flexible learning framework termed high-order spike-based information bottleneck (HOSIB) leveraging the surrogate gradient technique. The presented HOSIB framework, including second-order and third-order formation, i.e., second-order information bottleneck (SOIB) and third-order information bottleneck (TOIB), comprehensively explores the common latent architecture and the spike-based intrinsic information and discards the superfluous information in the data, which improves the generalization capability and robustness of SNN models. Specifically, HOSIB relies on the information bottleneck (IB) principle to prompt the sparse spike-based information representation and flexibly balance its exploitation and loss. Extensive classification experiments are conducted to empirically show the promising generalization ability of HOSIB. Furthermore, we apply the SOIB and TOIB algorithms in deep spiking convolutional networks to demonstrate their improvement in robustness with various categories of noise. The experimental results prove the HOSIB framework, especially TOIB, can achieve better generalization ability, robustness and power efficiency in comparison with the current representative studies.

A General DNA-Like Hybrid Symbiosis Framework: An EEG Cognitive Recognition Method

In electroencephalogram (EEG) cognitive recognition research, the combined use of artificial neural networks (ANNs) and spiking neural networks (SNNs) plays an important role to realize different categories of recognition tasks. However, most of the existing studies focus on the unidirectional interaction between an ANN and a SNN, which may be overly dependent on the performance of ANNs or SNNs. Inspired by the symbiosis phenomenon in nature, in this study, we propose a general DNA-like Hybrid Symbiosis (DNA-HS) framework, which enables mutual learning between the ANN and the SNN generated by this ANN through parametric genetic algorithm and bidirectional interaction mechanism to enhance the optimization ability of the model parameters, resulting in a significant improvement of the performance of the DNA-HS framework in all aspects. By comparing with seven typical EEG cognitive recognition models, the performance of the seven hybrid network frameworks constructed using this method on different EEG-based cognitive recognition tasks are all improved to different degrees, verifying the effectiveness of the proposed method. This unified hybrid network framework similar to the DNA structure is expected to open up a new approach and form a new research paradigm for EEG-based cognitive recognition task.

Trainable Reference Spikes Improve Temporal Information Processing of SNNs With Supervised Learning

Spiking neural networks (SNNs) are the next-generation neural networks composed of biologically plausible neurons that communicate through trains of spikes. By modifying the plastic parameters of SNNs, including weights and time delays, SNNs can be trained to perform various AI tasks, although in general not at the same level of performance as typical artificial neural networks (ANNs). One possible solution to improve the performance of SNNs is to consider plastic parameters other than just weights and time delays drawn from the inherent complexity of the neural system of the brain, which may help SNNs improve their information processing ability and achieve brainlike functions. Here, we propose reference spikes as a new type of plastic parameters in a supervised learning scheme in SNNs. A neuron receives reference spikes through synapses providing reference information independent of input to help during learning, whose number of spikes and timings are trainable by error backpropagation. Theoretically, reference spikes improve the temporal information processing of SNNs by modulating the integration of incoming spikes at a detailed level. Through comparative computational experiments, we demonstrate using supervised learning that reference spikes improve the memory capacity of SNNs to map input spike patterns to target output spike patterns and increase classification accuracy on the MNIST, Fashion-MNIST, and SHD data sets, where both input and target output are temporally encoded. Our results demonstrate that applying reference spikes improves the performance of SNNs by enhancing their temporal information processing ability.

Application of Event Cameras and Neuromorphic Computing to VSLAM: A Survey

Simultaneous Localization and Mapping (SLAM) is a crucial function for most autonomous systems, allowing them to both navigate through and create maps of unfamiliar surroundings. Traditional Visual SLAM, also commonly known as VSLAM, relies on frame-based cameras and structured processing pipelines, which face challenges in dynamic or low-light environments. However, recent advancements in event camera technology and neuromorphic processing offer promising opportunities to overcome these limitations. Event cameras inspired by biological vision systems capture the scenes asynchronously, consuming minimal power but with higher temporal resolution. Neuromorphic processors, which are designed to mimic the parallel processing capabilities of the human brain, offer efficient computation for real-time data processing of event-based data streams. This paper provides a comprehensive overview of recent research efforts in integrating event cameras and neuromorphic processors into VSLAM systems. It discusses the principles behind event cameras and neuromorphic processors, highlighting their advantages over traditional sensing and processing methods. Furthermore, an in-depth survey was conducted on state-of-the-art approaches in event-based SLAM, including feature extraction, motion estimation, and map reconstruction techniques. Additionally, the integration of event cameras with neuromorphic processors, focusing on their synergistic benefits in terms of energy efficiency, robustness, and real-time performance, was explored. The paper also discusses the challenges and open research questions in this emerging field, such as sensor calibration, data fusion, and algorithmic development. Finally, the potential applications and future directions for event-based SLAM systems are outlined, ranging from robotics and autonomous vehicles to augmented reality.

Gradient-free training of recurrent neural networks using random perturbations

Recurrent neural networks (RNNs) hold immense potential for computations due to their Turing completeness and sequential processing capabilities, yet existing methods for their training encounter efficiency challenges. Backpropagation through time (BPTT), the prevailing method, extends the backpropagation (BP) algorithm by unrolling the RNN over time. However, this approach suffers from significant drawbacks, including the need to interleave forward and backward phases and store exact gradient information. Furthermore, BPTT has been shown to struggle to propagate gradient information for long sequences, leading to vanishing gradients. An alternative strategy to using gradient-based methods like BPTT involves stochastically approximating gradients through perturbation-based methods. This learning approach is exceptionally simple, necessitating only forward passes in the network and a global reinforcement signal as feedback. Despite its simplicity, the random nature of its updates typically leads to inefficient optimization, limiting its effectiveness in training neural networks. In this study, we present a new approach to perturbation-based learning in RNNs whose performance is competitive with BPTT, while maintaining the inherent advantages over gradient-based learning. To this end, we extend the recently introduced activity-based node perturbation (ANP) method to operate in the time domain, leading to more efficient learning and generalization. We subsequently conduct a range of experiments to validate our approach. Our results show similar performance, convergence time and scalability when compared to BPTT, strongly outperforming standard node perturbation and weight perturbation methods. These findings suggest that perturbation-based learning methods offer a versatile alternative to gradient-based methods for training RNNs which can be ideally suited for neuromorphic computing applications.

Machine learning without a processor: Emergent learning in a nonlinear analog network

Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic contrastive local learning networks (CLLNs) offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here, we introduce a nonlinear CLLN-an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR (exclusive or) and nonlinear regression, without a computer. We find our decentralized system reduces modes of training error in order (mean, slope, curvature), similar to spectral bias in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning.

NIR sensors combined with chemometric algorithms in intelligent quality evaluation of sweetpotato roots from 'Farm' to 'Table': Progresses, challenges, trends, and prospects

NIR sensors, in conjunction with advanced chemometric algorithms, have proven to be a powerful and efficient tool for intelligent quality evaluation of sweetpotato roots throughout the entire supply chain. By leveraging NIR data in different wavelength ranges, the physicochemical, nutritional and antioxidant compositions, as well as variety classification of sweetpotato roots during the different stages were adequately evaluated, and all findings involving quantitative and qualitative investigations from the beginning to the present were summarized and analyzed comprehensively. All chemometric algorithms including both linear and nonlinear employed in NIR analysis of sweetpotato roots were introduced in detail and their calibration performances in terms of regression and classification were assessed and discussed. The challenges and limitations of current NIR application in quality evaluation of sweetpotato roots are emphasized. The prospects and trends covering the ongoing advancements in software and hardware are suggested to support the sustainable and efficient sweetpotato processing and utilization.

Lunar Lithium-7 Sensing (δ7Li): Spectral Patterns and Artificial Intelligence Techniques

Lithium, a critical natural resource integral to modern technology, has influenced diverse industries since its discovery in the 1950s. Of particular interest is lithium-7, the most prevalent lithium isotope on Earth, playing a vital role in applications such as batteries, metal alloys, medicine, and nuclear research. However, its extraction presents significant environmental and logistical challenges. This article explores the potential for lithium exploration on the Moon, driven by its value as a resource and the prospect of cost reduction due to the Moon's lower gravity, which holds promise for future space exploration endeavors. Additionally, the presence of lithium in the solar wind and its implications for material transport across celestial bodies are subjects of intrigue. Drawing from a limited dataset collected during the Apollo missions (Apollo 12, 15, 16, and 17) and leveraging artificial intelligence techniques and sample expansion through bootstrapping, this study develops predictive models for lithium-7 concentration based on spectral patterns. The study areas encompass the Aitken crater, Hadley Rima, and the Taurus-Littrow Valley, where higher lithium concentrations are observed in basaltic lunar regions. This research bridges lunar geology and the formation of the solar system, providing valuable insights into celestial resources and enhancing our understanding of space. The data used in this study were obtained from the imaging sensors (infrared, visible, and ultraviolet) of the Clementine satellite, which significantly contributed to the success of our research. Furthermore, the study addresses various aspects related to statistical analysis, sample quality validation, resampling, and bootstrapping. Supervised machine learning model training and validation, as well as data import and export, were explored. The analysis of data generated by the Clementine probe in the near-infrared (NIR) and ultraviolet-visible (UVVIS) spectra revealed evidence of the presence of lithium-7 (Li-7) on the lunar surface. The distribution of Li-7 on the lunar surface is non-uniform, with varying concentrations in different regions of the Moon identified, supporting the initial hypothesis associating surface Li-7 concentration with exposure to solar wind. While a direct numerical relationship between lunar topography and Li-7 concentration has not been established due to morphological diversity and methodological limitations, preliminary results suggest significant economic and technological potential in lunar lithium exploration and extraction.

Bioplausible Unsupervised Delay Learning for Extracting Spatiotemporal Features in Spiking Neural Networks

The plasticity of the conduction delay between neurons plays a fundamental role in learning temporal features that are essential for processing videos, speech, and many high-level functions. However, the exact underlying mechanisms in the brain for this modulation are still under investigation. Devising a rule for precisely adjusting the synaptic delays could eventually help in developing more efficient and powerful brain-inspired computational models. In this article, we propose an unsupervised bioplausible learning rule for adjusting the synaptic delays in spiking neural networks. We also provide the mathematical proofs to show the convergence of our rule in learning spatiotemporal patterns. Furthermore, to show the effectiveness of our learning rule, we conducted several experiments on random dot kinematogram and a subset of DVS128 Gesture data sets. The experimental results indicate the efficiency of applying our proposed delay learning rule in extracting spatiotemporal features in an STDP-based spiking neural network.

A universal ANN-to-SNN framework for achieving high accuracy and low latency deep Spiking Neural Networks

Spiking Neural Networks (SNNs) have become one of the most prominent next-generation computational models owing to their biological plausibility, low power consumption, and the potential for neuromorphic hardware implementation. Among the various methods for obtaining available SNNs, converting Artificial Neural Networks (ANNs) into SNNs is the most cost-effective approach. The early challenges in ANN-to-SNN conversion work revolved around the susceptibility of converted SNNs to conversion errors. Some recent endeavors have attempted to mitigate these conversion errors by altering the original ANNs. Despite their ability to enhance the accuracy of SNNs, these methods lack generality and cannot be directly applied to convert the majority of existing ANNs. In this paper, we present a framework named DNISNM for converting ANN to SNN, with the aim of addressing conversion errors arising from differences in the discreteness and asynchrony of network transmission between ANN and SNN. The DNISNM consists of two mechanisms, Data-based Neuronal Initialization (DNI) and Signed Neuron with Memory (SNM), designed to respectively address errors stemming from discreteness and asynchrony disparities. This framework requires no additional modifications to the original ANN and can result in SNNs with improved accuracy performance, simultaneously ensuring universality, high precision, and low inference latency. We verify it experimentally on challenging object recognition datasets, including CIFAR10, CIFAR100, and ImageNet-1k. Experimental results show that the SNN converted by our framework has very high accuracy even at extremely low latency.

Methodology based on spiking neural networks for univariate time-series forecasting

Spiking Neural Networks (SNN) are recognised as well-suited for processing spatiotemporal information with ultra-low energy consumption. However, proposals based on SNN for classification tasks are more common than for forecasting problems. In this sense, this paper presents a new general training methodology for univariate time-series forecasting based on SNN. The methodology is focused on one-step ahead forecasting problems and combines a PulseWidth Modulation based encoding-decoding algorithm with a Surrogate Gradient method as supervised training algorithm. In order to validate the generality of the presented methodology sine-wave, 3 UCI and 1 available real-world datasets are used. The results show very satisfactory forecasting results (MAE∈[0.0094,0.2891]) regardless of the characteristics of the dataset or the application field. In addition, weights can be initialised just once to achieve robust results, boosting the advantages of computational and energy cost of SNN.

Performance investigation of an active free-piston Stirling engine using artificial neural network and firefly optimization algorithm

The aim of this study is to explore the characteristics of an active Free-Piston Stirling Engine (AFPSE) through the use of machine learning methods. Due to the time-intensive nature of extracting simulation results from complex thermal equations, an Artificial Neural Network (ANN) is utilized to expedite the process. To construct a nonlinear model, 5000 samples are extracted from simulation results. Input parameters included in the model are the hot and cold source temperatures, the voltage given to the DC motor, spring stiffness, and the mass of the power piston, while output parameters are the amplitude and frequency of power piston displacement. The proposed ANN model structure comprises two hidden layer with 10 and 20 neurons, respectively, indicating the applicability of the ANN model in estimating significant parameters of AFPSE in a shorter amount of time. The firefly optimization algorithm is utilized to determine the unknown input parameters of ANN and maximize the output power. Results indicate that a maximum output power of 23.07 W can be attained by applying 8.5 V voltage on the DC motor. This study highlights the potential of machine learning techniques to explore the primary features of AFPSE.

SHIP: a computational framework for simulating and validating novel technologies in hardware spiking neural networks

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.

Machine learning in Alzheimer's disease drug discovery and target identification

Alzheimer's disease (AD) stands as a formidable neurodegenerative ailment that poses a substantial threat to the elderly population, with no known curative or disease-slowing drugs in existence. Among the vital and time-consuming stages in the drug discovery process, disease modeling and target identification hold particular significance. Disease modeling allows for a deeper comprehension of disease progression mechanisms and potential therapeutic avenues. On the other hand, target identification serves as the foundational step in drug development, exerting a profound influence on all subsequent phases and ultimately determining the success rate of drug development endeavors. Machine learning (ML) techniques have ushered in transformative breakthroughs in the realm of target discovery. Leveraging the strengths of large dataset analysis, multifaceted data processing, and the exploration of intricate biological mechanisms, ML has become instrumental in the quest for effective AD treatments. In this comprehensive review, we offer an account of how ML methodologies are being deployed in the pursuit of drug discovery for AD. Furthermore, we provide an overview of the utilization of ML in uncovering potential intervention strategies and prospective therapeutic targets for AD. Finally, we discuss the principal challenges and limitations currently faced by these approaches. We also explore the avenues for future research that hold promise in addressing these challenges.

First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures

Spiking neural networks (SNNs) are well-suited to process asynchronous event-based data. Most of the existing SNNs use rate-coding schemes that focus on firing rate (FR), and so they generally ignore the spike timing in events. On the contrary, methods based on temporal coding, particularly time-to-first-spike (TTFS) coding, can be accurate and efficient but they are difficult to train. Currently, there is limited research on applying TTFS coding to real events, since traditional TTFS-based methods impose one-spike constraint, which is not realistic for event-based data. In this study, we present a novel decision-making strategy based on first-spike (FS) coding that encodes FS timings of the output neurons to investigate the role of the first-spike timing in classifying real-world event sequences with complex temporal structures. To achieve FS coding, we propose a novel surrogate gradient learning method for discrete spike trains. In the forward pass, output spikes are encoded into discrete times to generate FS times. In the backpropagation, we develop an error assignment method that propagates error from FS times to spikes through a Gaussian window, and then supervised learning for spikes is implemented through a surrogate gradient approach. Additional strategies are introduced to facilitate the training of FS timings, such as adding empty sequences and employing different parameters for different layers. We make a comprehensive comparison between FS and FR coding in the experiments. Our results show that FS coding achieves comparable accuracy to FR coding while leading to superior energy efficiency and distinct neuronal dynamics on data sequences with very rich temporal structures. Additionally, a longer time delay in the first spike leads to higher accuracy, indicating important information is encoded in the timing of the first spike.

An Integrated Multi-Omics and Artificial Intelligence Framework for Advance Plant Phenotyping in Horticulture

This review discusses the transformative potential of integrating multi-omics data and artificial intelligence (AI) in advancing horticultural research, specifically plant phenotyping. The traditional methods of plant phenotyping, while valuable, are limited in their ability to capture the complexity of plant biology. The advent of (meta-)genomics, (meta-)transcriptomics, proteomics, and metabolomics has provided an opportunity for a more comprehensive analysis. AI and machine learning (ML) techniques can effectively handle the complexity and volume of multi-omics data, providing meaningful interpretations and predictions. Reflecting the multidisciplinary nature of this area of research, in this review, readers will find a collection of state-of-the-art solutions that are key to the integration of multi-omics data and AI for phenotyping experiments in horticulture, including experimental design considerations with several technical and non-technical challenges, which are discussed along with potential solutions. The future prospects of this integration include precision horticulture, predictive breeding, improved disease and stress response management, sustainable crop management, and exploration of plant biodiversity. The integration of multi-omics and AI holds immense promise for revolutionizing horticultural research and applications, heralding a new era in plant phenotyping.

Complex Oxides for Brain-Inspired Computing: A Review

The fields of brain-inspired computing, robotics, and, more broadly, artificial intelligence (AI) seek to implement knowledge gleaned from the natural world into human-designed electronics and machines. In this review, the opportunities presented by complex oxides, a class of electronic ceramic materials whose properties can be elegantly tuned by doping, electron interactions, and a variety of external stimuli near room temperature, are discussed. The review begins with a discussion of natural intelligence at the elementary level in the nervous system, followed by collective intelligence and learning at the animal colony level mediated by social interactions. An important aspect highlighted is the vast spatial and temporal scales involved in learning and memory. The focus then turns to collective phenomena, such as metal-to-insulator transitions (MITs), ferroelectricity, and related examples, to highlight recent demonstrations of artificial neurons, synapses, and circuits and their learning. First-principles theoretical treatments of the electronic structure, and in situ synchrotron spectroscopy of operating devices are then discussed. The implementation of the experimental characteristics into neural networks and algorithm design is then revewed. Finally, outstanding materials challenges that require a microscopic understanding of the physical mechanisms, which will be essential for advancing the frontiers of neuromorphic computing, are highlighted.

Applications, functions, and accuracy of artificial intelligence in restorative dentistry: A literature review

OBJECTIVE

The applications of artificial intelligence (AI) are increasing in restorative dentistry; however, the AI performance is unclear for dental professionals. The purpose of this narrative review was to evaluate the applications, functions, and accuracy of AI in diverse aspects of restorative dentistry including caries detection, tooth preparation margin detection, tooth restoration design, metal structure casting, dental restoration/implant detection, removable partial denture design, and tooth shade determination.

OVERVIEW

An electronic search was performed on Medline/PubMed, Embase, Web of Science, Cochrane, Scopus, and Google Scholar databases. English-language articles, published from January 1, 2000, to March 1, 2022, relevant to the aforementioned aspects were selected using the key terms of artificial intelligence, machine learning, deep learning, artificial neural networks, convolutional neural networks, clustering, soft computing, automated planning, computational learning, computer vision, and automated reasoning as inclusion criteria. A manual search was also performed. Therefore, 157 articles were included, reviewed, and discussed.

CONCLUSIONS

Based on the current literature, the AI models have shown promising performance in the mentioned aspects when being compared with traditional approaches in terms of accuracy; however, as these models are still in development, more studies are required to validate their accuracy and apply them to routine clinical practice.

CLINICAL SIGNIFICANCE

AI with its specific functions has shown successful applications with acceptable accuracy in diverse aspects of restorative dentistry. The understanding of these functions may lead to novel applications with optimal accuracy for AI in restorative dentistry.

Exploring spiking neural networks: a comprehensive analysis of mathematical models and applications

This article presents a comprehensive analysis of spiking neural networks (SNNs) and their mathematical models for simulating the behavior of neurons through the generation of spikes. The study explores various models, including LIF and NLIF, for constructing SNNs and investigates their potential applications in different domains. However, implementation poses several challenges, including identifying the most appropriate model for classification tasks that demand high accuracy and low-performance loss. To address this issue, this research study compares the performance, behavior, and spike generation of multiple SNN models using consistent inputs and neurons. The findings of the study provide valuable insights into the benefits and challenges of SNNs and their models, emphasizing the significance of comparing multiple models to identify the most effective one. Moreover, the study quantifies the number of spiking operations required by each model to process the same inputs and produce equivalent outputs, enabling a thorough assessment of computational efficiency. The findings provide valuable insights into the benefits and limitations of SNNs and their models. The research underscores the significance of comparing different models to make informed decisions in practical applications. Additionally, the results reveal essential variations in biological plausibility and computational efficiency among the models, further emphasizing the importance of selecting the most suitable model for a given task. Overall, this study contributes to a deeper understanding of SNNs and offers practical guidelines for using their potential in real-world scenarios.

ReplaceNet: real-time replacement of a biological neural circuit with a hardware-assisted spiking neural network

Recent developments in artificial neural networks and their learning algorithms have enabled new research directions in computer vision, language modeling, and neuroscience. Among various neural network algorithms, spiking neural networks (SNNs) are well-suited for understanding the behavior of biological neural circuits. In this work, we propose to guide the training of a sparse SNN in order to replace a sub-region of a cultured hippocampal network with limited hardware resources. To verify our approach with a realistic experimental setup, we record spikes of cultured hippocampal neurons with a microelectrode array (in vitro). The main focus of this work is to dynamically cut unimportant synapses during SNN training on the fly so that the model can be realized on resource-constrained hardware, e.g., implantable devices. To do so, we adopt a simple STDP learning rule to easily select important synapses that impact the quality of spike timing learning. By combining the STDP rule with online supervised learning, we can precisely predict the spike pattern of the cultured network in real-time. The reduction in the model complexity, i.e., the reduced number of connections, significantly reduces the required hardware resources, which is crucial in developing an implantable chip for the treatment of neurological disorders. In addition to the new learning algorithm, we prototype a sparse SNN hardware on a small FPGA with pipelined execution and parallel computing to verify the possibility of real-time replacement. As a result, we can replace a sub-region of the biological neural circuit within 22 μs using 2.5 × fewer hardware resources, i.e., by allowing 80% sparsity in the SNN model, compared to the fully-connected SNN model. With energy-efficient algorithms and hardware, this work presents an essential step toward real-time neuroprosthetic computation.

Incorporating structural plasticity into self-organization recurrent networks for sequence learning

Introduction

Spiking neural networks (SNNs), inspired by biological neural networks, have received a surge of interest due to its temporal encoding. Biological neural networks are driven by multiple plasticities, including spike timing-dependent plasticity (STDP), structural plasticity, and homeostatic plasticity, making network connection patterns and weights to change continuously during the lifecycle. However, it is unclear how these plasticities interact to shape neural networks and affect neural signal processing.

Method

Here, we propose a reward-modulated self-organization recurrent network with structural plasticity (RSRN-SP) to investigate this issue. Specifically, RSRN-SP uses spikes to encode information, and incorporate multiple plasticities including reward-modulated spike timing-dependent plasticity (R-STDP), homeostatic plasticity, and structural plasticity. On the one hand, combined with homeostatic plasticity, R-STDP is presented to guide the updating of synaptic weights. On the other hand, structural plasticity is utilized to simulate the growth and pruning of synaptic connections.

Results and discussion

Extensive experiments for sequential learning tasks are conducted to demonstrate the representational ability of the RSRN-SP, including counting task, motion prediction, and motion generation. Furthermore, the simulations also indicate that the characteristics arose from the RSRN-SP are consistent with biological observations.

A regularization perspective based theoretical analysis for adversarial robustness of deep spiking neural networks

Spiking Neural Network (SNN) has been recognized as the third generation of neural networks. Conventionally, a SNN can be converted from a pre-trained Artificial Neural Network (ANN) with less computation and memory than training from scratch. But, these converted SNNs are vulnerable to adversarial attacks. Numerical experiments demonstrate that the SNN trained by optimizing the loss function will be more adversarial robust, but the theoretical analysis for the mechanism of robustness is lacking. In this paper, we provide a theoretical explanation by analyzing the expected risk function. Starting by modeling the stochastic process introduced by the Poisson encoder, we prove that there is a positive semidefinite regularizer. Perhaps surprisingly, this regularizer can make the gradients of the output with respect to input closer to zero, thus resulting in inherent robustness against adversarial attacks. Extensive experiments on the CIFAR10 and CIFAR100 datasets support our point of view. For example, we find that the sum of squares of the gradients of the converted SNNs is 13∼160 times that of the trained SNNs. And, the smaller the sum of the squares of the gradients, the smaller the degradation of accuracy under adversarial attack.

All-optical spiking neural network and optical spike-time-dependent plasticity based on the self-pulsing effect within a micro-ring resonator

In this paper, we proposed an all-optical version of photonic spiking neurons and spike-time-dependent plasticity (STDP) based on the nonlinear optical effects within a micro-ring resonator. In this system, the self-pulsing effect was exploited to implement threshold control, and the equivalent pulse energy required for spiking, calculated by multiplying the input pulse power amplitude with its duration, was about 14.1 pJ. The positive performance of the neurons in the excitability and cascadability tests validated the feasibility of this scheme. Furthermore, two simulations were performed to demonstrate that such an all-optical spiking neural network incorporated with STDP could run stably on a stochastic topology. The essence of such an all-optical spiking neural network is a nonlinear spiking dynamical system that combines the advantages of photonics and spiking neural networks (SNNs), promising access to the high speed and lower consumption inherent to optical systems.

Direct learning-based deep spiking neural networks: a review

The spiking neural network (SNN), as a promising brain-inspired computational model with binary spike information transmission mechanism, rich spatially-temporal dynamics, and event-driven characteristics, has received extensive attention. However, its intricately discontinuous spike mechanism brings difficulty to the optimization of the deep SNN. Since the surrogate gradient method can greatly mitigate the optimization difficulty and shows great potential in directly training deep SNNs, a variety of direct learning-based deep SNN works have been proposed and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these direct learning-based deep SNN works, mainly categorized into accuracy improvement methods, efficiency improvement methods, and temporal dynamics utilization methods. In addition, we also divide these categorizations into finer granularities further to better organize and introduce them. Finally, the challenges and trends that may be faced in future research are prospected.

Multitask computation through dynamics in recurrent spiking neural networks

In this work, inspired by cognitive neuroscience experiments, we propose recurrent spiking neural networks trained to perform multiple target tasks. These models are designed by considering neurocognitive activity as computational processes through dynamics. Trained by input-output examples, these spiking neural networks are reverse engineered to find the dynamic mechanisms that are fundamental to their performance. We show that considering multitasking and spiking within one system provides insightful ideas on the principles of neural computation.

Origin of the efficiency of spike timing-based neural computation for processing temporal information

Although the advantage of spike timing-based over rate-based network computation has been recognized, the underlying mechanism remains unclear. Using Tempotron and Perceptron as elementary neural models, we examined the intrinsic difference between spike timing-based and rate-based computations. For more direct comparison, we modified Tempotron computation into rate-based computation with the retention of some temporal information. Previous studies have shown that spike timing-based computation are computationally more powerful than rate-based computation in terms of the number of computational units required and the capability in classifying random patterns. Our study showed that spike timing-based and rate-based Tempotron computations provided similar capability in classifying random spike patterns, as well as in text sentiment classification and spam text detection. However, spike timing-based computation is superior in performing a task involving discriminating forward vs. reverse sequence of events, i.e., information mainly temporal in nature. Further studies revealed that this superiority required the asymmetry in the profile of the postsynaptic potential (PSP), and that temporal sequence information was converted to biased spatial distribution of synaptic weight modifications during learning. Thus, the intrinsic PSP asymmetry is a mechanistic basis for the high efficiency of spike timing-based computation for processing temporal information.

Single dendritic neural classification with an effective spherical search-based whale learning algorithm

McCulloch-Pitts neuron-based neural networks have been the mainstream deep learning methods, achieving breakthrough in various real-world applications. However, McCulloch-Pitts neuron is also under longtime criticism of being overly simplistic. To alleviate this issue, the dendritic neuron model (DNM), which employs non-linear information processing capabilities of dendrites, has been widely used for prediction and classification tasks. In this study, we innovatively propose a hybrid approach to co-evolve DNM in contrast to back propagation (BP) techniques, which are sensitive to initial circumstances and readily fall into local minima. The whale optimization algorithm is improved by spherical search learning to perform co-evolution through dynamic hybridizing. Eleven classification datasets were selected from the well-known UCI Machine Learning Repository. Its efficiency in our model was verified by statistical analysis of convergence speed and Wilcoxon sign-rank tests, with receiver operating characteristic curves and the calculation of area under the curve. In terms of classification accuracy, the proposed co-evolution method beats 10 existing cutting-edge non-BP methods and BP, suggesting that well-learned DNMs are computationally significantly more potent than conventional McCulloch-Pitts types and can be employed as the building blocks for the next-generation deep learning methods.

S3NN: Time step reduction of spiking surrogate gradients for training energy efficient single-step spiking neural networks

As the scales of neural networks increase, techniques that enable them to run with low computational cost and energy efficiency are required. From such demands, various efficient neural network paradigms, such as spiking neural networks (SNNs) or binary neural networks (BNNs), have been proposed. However, they have sticky drawbacks, such as degraded inference accuracy and latency. To solve these problems, we propose a single-step spiking neural network (S³NN), an energy-efficient neural network with low computational cost and high precision. The proposed S³NN processes the information between hidden layers by spikes as SNNs. Nevertheless, it has no temporal dimension so that there is no latency within training and inference phases as BNNs. Thus, the proposed S³NN has a lower computational cost than SNNs that require time-series processing. However, S³NN cannot adopt naïve backpropagation algorithms due to the non-differentiability nature of spikes. We deduce a suitable neuron model by reducing the surrogate gradient for multi-time step SNNs to a single-time step. We experimentally demonstrated that the obtained surrogate gradient allows S³NN to be trained appropriately. We also showed that the proposed S³NN could achieve comparable accuracy to full-precision networks while being highly energy-efficient.

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics

The world today is witnessing the significant role and huge demand for molecular detection and screening in healthcare and medical diagnosis, especially during the outbreak of COVID-19. Surface-enhanced spectroscopy techniques, including Surface-Enhanced Raman Scattering (SERS) and Infrared Absorption (SEIRA), provide lattice and molecular vibrational fingerprint information which is directly linked to the molecular constituents, chemical bonds, and configuration. These properties make them an unambiguous, nondestructive, and label-free toolkit for molecular diagnostics and screening. However, new issues in molecular diagnostics, such as increasing molecular species, faster spread of viruses, and higher requirements for detection accuracy and sensitivity, have brought great challenges to detection technology. Advancements in artificial intelligence and machine learning (ML) techniques show promising potential in empowering SERS and SEIRA with rapid analysis and automatic data processing to jointly tackle the challenge. This review introduces the combination of ML and SERS/SEIRA by investigating how ML algorithms can be beneficial to SERS/SEIRA, discussing the general process of combining ML and SEIRA/SERS, highlighting the molecular diagnostics and screening applications based on ML-combined SEIRA/SERS, and providing perspectives on the future development of ML-integrated SEIRA/SERS. In general, this review offers comprehensive knowledge about the recent advances and the future outlook regarding ML-integrated SEIRA/SERS for molecular diagnostics and screening.

Supervised Learning Algorithm Based on Spike Train Inner Product for Deep Spiking Neural Networks

By mimicking the hierarchical structure of human brain, deep spiking neural networks (DSNNs) can extract features from a lower level to a higher level gradually, and improve the performance for the processing of spatio-temporal information. Due to the complex hierarchical structure and implicit nonlinear mechanism, the formulation of spike train level supervised learning methods for DSNNs remains an important problem in this research area. Based on the definition of kernel function and spike trains inner product (STIP) as well as the idea of error backpropagation (BP), this paper firstly proposes a deep supervised learning algorithm for DSNNs named BP-STIP. Furthermore, in order to alleviate the intrinsic weight transport problem of the BP mechanism, feedback alignment (FA) and broadcast alignment (BA) mechanisms are utilized to optimize the error feedback mode of BP-STIP, and two deep supervised learning algorithms named FA-STIP and BA-STIP are also proposed. In the experiments, the effectiveness of the proposed three DSNN algorithms is verified on the MNIST digital image benchmark dataset, and the influence of different kernel functions on the learning performance of DSNNs with different network scales is analyzed. Experimental results show that the FA-STIP and BP-STIP algorithms can achieve 94.73% and 95.65% classification accuracy, which apparently possess better learning performance and stability compared with the benchmark algorithm BP-STIP.

Introducing the Dendrify framework for incorporating dendrites to spiking neural networks

Computational modeling has been indispensable for understanding how subcellular neuronal features influence circuit processing. However, the role of dendritic computations in network-level operations remains largely unexplored. This is partly because existing tools do not allow the development of realistic and efficient network models that account for dendrites. Current spiking neural networks, although efficient, are usually quite simplistic, overlooking essential dendritic properties. Conversely, circuit models with morphologically detailed neuron models are computationally costly, thus impractical for large-network simulations. To bridge the gap between these two extremes and facilitate the adoption of dendritic features in spiking neural networks, we introduce Dendrify, an open-source Python package based on Brian 2. Dendrify, through simple commands, automatically generates reduced compartmental neuron models with simplified yet biologically relevant dendritic and synaptic integrative properties. Such models strike a good balance between flexibility, performance, and biological accuracy, allowing us to explore dendritic contributions to network-level functions while paving the way for developing more powerful neuromorphic systems.

A Review on Machine Learning Applications for Solar Plants

A solar plant system has complex nonlinear dynamics with uncertainties due to variations in system parameters and insolation. Thereby, it is difficult to approximate these complex dynamics with conventional algorithms whereas Machine Learning (ML) methods yield the essential performance required. ML models are key units in recent sensor systems for solar plant design, forecasting, maintenance, and control to provide the best safety, reliability, robustness, and performance as compared to classical methods which are usually employed in the hardware and software of solar plants. Considering this, the goal of our paper is to explore and analyze ML technologies and their advantages and shortcomings as compared to classical methods for the design, forecasting, maintenance, and control of solar plants. In contrast with other review articles, our research briefly summarizes our intelligent, self-adaptive models for sizing, forecasting, maintenance, and control of a solar plant; sets benchmarks for performance comparison of the reviewed ML models for a solar plant's system; proposes a simple but effective integration scheme of an ML sensor solar plant system's implementation and outlines its future digital transformation into a smart solar plant based on the integrated cutting-edge technologies; and estimates the impact of ML technologies based on the proposed scheme on a solar plant value chain.

BSNN: Towards faster and better conversion of artificial neural networks to spiking neural networks with bistable neurons

The spiking neural network (SNN) computes and communicates information through discrete binary events. Recent work has achieved essential progress on an excellent performance by converting ANN to SNN. Due to the difference in information processing, the converted deep SNN usually suffers serious performance loss and large time delay. In this paper, we analyze the reasons for the performance loss and propose a novel bistable spiking neural network (BSNN) that addresses the problem of the phase lead and phase lag. Also, we design synchronous neurons (SN) to help efficiently improve performance when ResNet structure-based ANNs are converted. BSNN significantly improves the performance of the converted SNN by enabling more accurate delivery of information to the next layer after one cycle. Experimental results show that the proposed method only needs 1/4-1/10 of the time steps compared to previous work to achieve nearly lossless conversion. We demonstrate better ANN-SNN conversion for VGG16, ResNet20, and ResNet34 on challenging datasets including CIFAR-10 (95.16% top-1), CIFAR-100 (78.12% top-1), and ImageNet (72.64% top-1).

Linear leaky-integrate-and-fire neuron model based spiking neural networks and its mapping relationship to deep neural networks

Spiking neural networks (SNNs) are brain-inspired machine learning algorithms with merits such as biological plausibility and unsupervised learning capability. Previous works have shown that converting Artificial Neural Networks (ANNs) into SNNs is a practical and efficient approach for implementing an SNN. However, the basic principle and theoretical groundwork are lacking for training a non-accuracy-loss SNN. This paper establishes a precise mathematical mapping between the biological parameters of the Linear Leaky-Integrate-and-Fire model (LIF)/SNNs and the parameters of ReLU-AN/Deep Neural Networks (DNNs). Such mapping relationship is analytically proven under certain conditions and demonstrated by simulation and real data experiments. It can serve as the theoretical basis for the potential combination of the respective merits of the two categories of neural networks.

Spiking VGG7: Deep Convolutional Spiking Neural Network with Direct Training for Object Recognition

We propose a deep convolutional spiking neural network (DCSNN) with direct training to classify concrete bridge damage in a real engineering environment. The leaky-integrate-and-fire (LIF) neuron model is employed in our DCSNN that is similar to VGG. Poisson encoding and convolution encoding strategies are considered. The gradient surrogate method is introduced to realize the supervised training for the DCSNN. In addition, we have examined the effect of observation time step on the network performance. The testing performance for two different spike encoding strategies are compared. The results show that the DCSNN using gradient surrogate method can achieve a performance of 97.83%, which is comparable to traditional CNN. We also present a comparison with STDP-based unsupervised learning and a converted algorithm, and the proposed DCSNN is proved to have the best performance. To demonstrate the generalization performance of the model, we also use a public dataset for comparison. This work paves the way for the practical engineering applications of the deep SNNs.

A Spike Neural Network Model for Lateral Suppression of Spike-Timing-Dependent Plasticity with Adaptive Threshold

Aiming at the practical constraints of high resource occupancy and complex calculations in the existing Spike Neural Network (SNN) image classification model, in order to seek a more lightweight and efficient machine vision solution, this paper proposes an adaptive threshold Spike Neural Network (SNN) model of lateral inhibition of Spike-Timing-Dependent Plasticity (STDP). The conversion from grayscale image to pulse sequence is completed by convolution normalization and first pulse time coding. The network self-classification is realized by combining the classical Spike-Timing-Dependent Plasticity algorithm (STDP) and lateral suppression algorithm. The occurrence of overfitting is effectively suppressed by introducing an adaptive threshold. The experimental results on the MNIST data set show that compared with the traditional SNN classification model, the complexity of the weight update algorithm is reduced from O(n2) to O(1), and the accuracy rate can still remain stable at about 96%. The provided model is conducive to the migration of software algorithms to the bottom layer of the hardware platform, and can provide a reference for the realization of edge computing solutions for small intelligent hardware terminals with high efficiency and low power consumption.

Optimizing the Neural Structure and Hyperparameters of Liquid State Machines Based on Evolutionary Membrane Algorithm

As one of the important artificial intelligence fields, brain-like computing attempts to give machines a higher intelligence level by studying and simulating the cognitive principles of the human brain. A spiking neural network (SNN) is one of the research directions of brain-like computing, characterized by better biogenesis and stronger computing power than the traditional neural network. A liquid state machine (LSM) is a neural computing model with a recurrent network structure based on SNN. In this paper, a learning algorithm based on an evolutionary membrane algorithm is proposed to optimize the neural structure and hyperparameters of an LSM. First, the object of the proposed algorithm is designed according to the neural structure and hyperparameters of the LSM. Second, the reaction rules of the proposed algorithm are employed to discover the best neural structure and hyperparameters of the LSM. Third, the membrane structure is that the skin membrane contains several elementary membranes to speed up the search of the proposed algorithm. In the simulation experiment, effectiveness verification is carried out on the MNIST and KTH datasets. In terms of the MNIST datasets, the best test results of the proposed algorithm with 500, 1000 and 2000 spiking neurons are 86.8%, 90.6% and 90.8%, respectively. The best test results of the proposed algorithm on KTH with 500, 1000 and 2000 spiking neurons are 82.9%, 85.3% and 86.3%, respectively. The simulation results show that the proposed algorithm has a more competitive advantage than other experimental algorithms.