Memristors, as memristive devices, have received a great deal of interest since being fabricated by HP labs. The forgetting effect that has significant influences on memristors＇ performance has to be taken into accou...Memristors, as memristive devices, have received a great deal of interest since being fabricated by HP labs. The forgetting effect that has significant influences on memristors＇ performance has to be taken into account when they are employed. It is significant to build a good model that can express the forgetting effect well for application researches due to its promising prospects in brain-inspired computing. Some models are proposed to represent the forgetting effect but do not work well. In this paper, we present a novel window function, which has good performance in a drift model. We analyze the deficiencies of the previous drift diffusion models for the forgetting effect and propose an improved model. Moreover,the improved model is exploited as a synapse model in spiking neural networks to recognize digit images. Simulation results show that the improved model overcomes the defects of the previous models and can be used as a synapse model in brain-inspired computing due to its synaptic characteristics. The results also indicate that the improved model can express the forgetting effect better when it is employed in spiking neural networks, which means that more appropriate evaluations can be obtained in applications.展开更多
By definition, bionics is the application of biological mechanisms found in nature to artificial systems in order to achieve specific functional goals. Successful examples range from Velcro, the touch fastener inspire...By definition, bionics is the application of biological mechanisms found in nature to artificial systems in order to achieve specific functional goals. Successful examples range from Velcro, the touch fastener inspired by the hooks of burrs, to self-cleaning material, inspired by the surface of the lotus leaf. Recently, a new trend in bionics i Brain-Inspired Computing （BIC） - has captured increasing attention. Instead of learning from burrs and leaves, BIC aims to understand the brain and then utilize its operating principles to achieve powerful and efficient information processing.展开更多
Recent advances in Artificial Intelligence(AI)have indicated that inspirations from the brain can effectively improve the level of intelligence for AI computational models,even if just local and partial inspirations.N...Recent advances in Artificial Intelligence(AI)have indicated that inspirations from the brain can effectively improve the level of intelligence for AI computational models,even if just local and partial inspirations.Nevertheless,realizing and exceeding intelligence at a human level still needs a deeper investigation and inspirations from the brain.The goal of brain-inspired intelligence is to achieve human intelligence inspired from brain neural mechanism and cognitive behavior mechanism.To this end,in this paper we introduce the relationship between AI and neuroscience,the current status of brain-inspired intelligence,the future work in intelligent control systems,and its profound influence in other fields.展开更多
Recently,the brain-inspired mechanisms beneficial to efficient navigation in mammals have exhibited huge research potential.Specifically,the geometry cell model has shown significant insights into the ability of mamma...Recently,the brain-inspired mechanisms beneficial to efficient navigation in mammals have exhibited huge research potential.Specifically,the geometry cell model has shown significant insights into the ability of mammals,which is used to model the geometric information of their surroundings during movement.Meanwhile,the process of general exploration will consume large amounts of computing resources when agents with high-performance computing equipment accomplish autonomous tasks.This paper focuses on the long-range autonomous exploration and navigation tasks in which they are conducted by agents within complex indoor and outdoor environments.To reduce the computational demands,we propose a framework integrating the Brain-Inspired Geometry-awareness namely BIG for two autonomous tasks.The exploration task named BIG-Explorer involves efficiently searching untouched areas by embedding the geometry cell model.It identifies expanding frontiers using geometric assigners and takes into account relevant factors such as boundary information.The navigation task named BIG-Navigator builds upon insights gained during the exploration phase and guides agents to a predefined destination.We conduct comprehensive experimental assessments within third-party simulation environments.The evaluation metrics employed in this paper include the number of nodes,the length of a path,algorithm execution time,and the size of exploration space.Finally,the results of the evaluation demonstrate that the incorporation of geometry cell model increases the efficiency in both exploration and navigation processes by at least 20%,compared with four benchmark methods.展开更多
Efficiently predicting effluent quality through data-driven analysis presents a significant advancement for consistent wastewater treatment operations.In this study,we aimed to develop an integrated method for predict...Efficiently predicting effluent quality through data-driven analysis presents a significant advancement for consistent wastewater treatment operations.In this study,we aimed to develop an integrated method for predicting effluent COD and NH3 levels.We employed a 200 L pilot-scale sequencing batch reactor(SBR)to gather multimodal data from urban sewage over 40 d.Then we collected data on critical parameters like COD,DO,pH,NH_(3),EC,ORP,SS,and water temperature,alongside wastewater surface images,resulting in a data set of approximately 40246 points.Then we proposed a brain-inspired image and temporal fusion model integrated with a CNN-LSTM network(BITF-CL)using this data.This innovative model synergized sewage imagery with water quality data,enhancing prediction accuracy.As a result,the BITF-CL model reduced prediction error by over 23%compared to traditional methods and still performed comparably to conventional techniques even without using DO and SS sensor data.Consequently,this research presents a cost-effective and precise prediction system for sewage treatment,demonstrating the potential of brain-inspired models.展开更多
Brain-inspired computing is a new technology that draws on the principles of brain science and is oriented to the efficient development of artificial general intelligence(AGI),and a brain-inspired computing system is ...Brain-inspired computing is a new technology that draws on the principles of brain science and is oriented to the efficient development of artificial general intelligence(AGI),and a brain-inspired computing system is a hierarchical system composed of neuromorphic chips,basic software and hardware,and algorithms/applications that embody this tech-nology.While the system is developing rapidly,it faces various challenges and opportunities brought by interdisciplinary research,including the issue of software and hardware fragmentation.This paper analyzes the status quo of brain-inspired computing systems.Enlightened by some design principle and methodology of general-purpose computers,it is proposed to construct"general-purpose"brain-inspired computing systems.A general-purpose brain-inspired computing system refers to a brain-inspired computing hierarchy constructed based on the design philosophy of decoupling software and hardware,which can flexibly support various brain-inspired computing applications and neuromorphic chips with different architec-tures.Further,this paper introduces our recent work in these aspects,including the ANN(artificial neural network)/SNN(spiking neural network)development tools,the hardware agnostic compilation infrastructure,and the chip micro-archi-tecture with high flexibility of programming and high performance;these studies show that the"general-purpose"system can remarkably improve the efficiency of application development and enhance the productivity of basic software,thereby being conductive to accelerating the advancement of various brain-inspired algorithms and applications.We believe that this is the key to the collaborative research and development,and the evolution of applications,basic software and chips in this field,and conducive to building a favorable software/hardware ecosystem of brain-inspired computing.展开更多
In recent years,the urbanization process has brought modernity while also causing key issues,such as traffic congestion and parking conflicts.Therefore,cities need a more intelligent"brain"to form more intel...In recent years,the urbanization process has brought modernity while also causing key issues,such as traffic congestion and parking conflicts.Therefore,cities need a more intelligent"brain"to form more intelligent and efficient transportation systems.At present,as a type of machine learning,the traditional clustering algorithm still has limitations.K-means algorithm is widely used to solve traffic clustering problems,but it has limitations,such as sensitivity to initial points and poor robustness.Therefore,based on the hybrid architecture of Quantum Annealing(QA)and brain-inspired cognitive computing,this study proposes QA and Brain-Inspired Clustering Algorithm(QABICA)to solve the problem of urban taxi-stand locations.Based on the traffic trajectory data of Xi’an and Chengdu provided by Didi Chuxing,the clustering results of our algorithm and K-means algorithm are compared.We find that the average taxi-stand location bias of the final result based on QABICA is smaller than that based on K-means,and the bias of our algorithm can effectively reduce the tradition K-means bias by approximately 42%,up to approximately 83%,with higher robustness.QA algorithm is able to jump out of the local suboptimal solutions and approach the global optimum,and brain-inspired cognitive computing provides search feedback and direction.Thus,we will further consider applying our algorithm to analyze urban traffic flow,and solve traffic congestion and other key problems in intelligent transportation.展开更多
Traditional joint-link robots have been widely used in production lines because of their high precision for single tasks.With the development of the manufacturing and service industries,the requirement for the compreh...Traditional joint-link robots have been widely used in production lines because of their high precision for single tasks.With the development of the manufacturing and service industries,the requirement for the comprehensive performance of robotics is growing.Numerous types of bio-inspired robotics have been investigated to realize human-like motion control and manipulation.A study route from inner mechanisms to external structures is proposed to imitate humans and animals better.With this idea,a brain-inspired intelligent robotic system is constructed that contains visual cognition,decision-making,motion control,and musculoskeletal structures.This paper reviews cutting-edge research in brain-inspired visual cognition,decision-making,motion control,and musculoskeletal systems.Two software systems and a corresponding hardware system are established,aiming at the verification and applications of next-generationbrain-inspired musculoskeletal robots.展开更多
Brain-inspired computer vision aims to learn from biological systems to develop advanced image processing techniques.However,its progress so far is not impressing.We recognize that a main obstacle comes from that the ...Brain-inspired computer vision aims to learn from biological systems to develop advanced image processing techniques.However,its progress so far is not impressing.We recognize that a main obstacle comes from that the current paradigm for brain-inspired computer vision has not captured the fundamental nature of biological vision,i.e.,the biological vision is targeted for processing spatio-temporal patterns.Recently,a new paradigm for developing brain-inspired computer vision is emerging,which emphasizes on the spatio-temporal nature of visual signals and the brain-inspired models for processing this type of data.In this paper,we review some recent primary works towards this new paradigm,including the development of spike cameras which acquire spiking signals directly from visual scenes,and the development of computational models learned from neural systems that are specialized to process spatio-temporal patterns,including models for object detection,tracking,and recognition.We also discuss about the future directions to improve the paradigm.展开更多
Brain-inspired computing refers to computational models,methods,and systems,that are mainly inspired by the processing mode or structure of brain.A recent study proposed the concept of"neuromorphic completeness&q...Brain-inspired computing refers to computational models,methods,and systems,that are mainly inspired by the processing mode or structure of brain.A recent study proposed the concept of"neuromorphic completeness"and the corresponding system hierarchy,which is helpful to determine the capability boundary of brain-inspired computing system and to judge whether hardware and software of brain-inspired computing are compatible with each other.As a position paper,this article analyzes the existing brain-inspired chips design characteristics and the current so-called"general purpose"application development frameworks for brain-inspired computing,as well as introduces the background and the potential of this proposal.Further,some key features of this concept are presented through the comparison with the Turing completeness and approximate computation,and the analyses of the relationship with"general-purpose"brain-inspired computing systems(it means that computing systems can support all computable applications).In the end,a promising technical approach to realize such computing systems is introduced,as well as the on-going research and the work foundation.We believe that this work is conducive to the design of extensible neuromorphic complete hardware-primitives and the corresponding chips.On this basis,it is expected to gradually realize"general purpose"brain-inspired computing system,in order to take into account the functionality completeness and application efficiency.展开更多
Visual recognition is currently one of the most important and active research areas in computer vision,pattern recognition,and even the general field of artificial intelligence.It has great fundamental importance and ...Visual recognition is currently one of the most important and active research areas in computer vision,pattern recognition,and even the general field of artificial intelligence.It has great fundamental importance and strong industrial needs,particularly the modern deep neural networks(DNNs)and some brain-inspired methodologies,have largely boosted the recognition performance on many concrete tasks,with the help of large amounts of training data and new powerful computation resources.Although recognition accuracy is usually the first concern for new progresses,efficiency is actually rather important and sometimes critical for both academic research and industrial applications.Moreover,insightful views on the opportunities and challenges of efficiency are also highly required for the entire community.While general surveys on the efficiency issue have been done from various perspectives,as far as we are aware,scarcely any of them focused on visual recognition systematically,and thus it is unclear which progresses are applicable to it and what else should be concerned.In this survey,we present the review of recent advances with our suggestions on the new possible directions towards improving the efficiency of DNN-related and brain-inspired visual recognition approaches,including efficient network compression and dynamic brain-inspired networks.We investigate not only from the model but also from the data point of view(which is not the case in existing surveys)and focus on four typical data types(images,video,points,and events).This survey attempts to provide a systematic summary via a comprehensive survey that can serve as a valuable reference and inspire both researchers and practitioners working on visual recognition problems.展开更多
Modern computational models have leveraged biological advances in human brain research. This study addresses the problem of multimodal learning with the help of brain-inspired models. Specifically, a unified multimoda...Modern computational models have leveraged biological advances in human brain research. This study addresses the problem of multimodal learning with the help of brain-inspired models. Specifically, a unified multimodal learning architecture is proposed based on deep neural networks, which are inspired by the biology of the visual cortex of the human brain. This unified framework is validated by two practical multimodal learning tasks: image captioning, involving visual and natural language signals, and visual-haptic fusion, involving haptic and visual signals. Extensive experiments are conducted under the framework, and competitive results are achieved.展开更多
Despite its great success,deep learning severely suffers from robustness;i.e.,deep neural networks are very vulnerable to adversarial attacks,even the simplest ones.Inspired by recent advances in brain science,we prop...Despite its great success,deep learning severely suffers from robustness;i.e.,deep neural networks are very vulnerable to adversarial attacks,even the simplest ones.Inspired by recent advances in brain science,we propose the denoised internal models(DIM),a novel generative autoencoder-based model to tackle this challenge.Simulating the pipeline in the human brain for visual signal processing,DIM adopts a two-stage approach.In the first stage,DIM uses a denoiser to reduce the noise and the dimensions of inputs,reflecting the information pre-processing in the thalamus.Inspired by the sparse coding of memory-related traces in the primary visual cortex,the second stage produces a set of internal models,one for each category.We evaluate DIM over 42 adversarial attacks,showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness on the MNIST(Modified National Institute of Standards and Technology)dataset.展开更多
Brain,the material foundation of human intelligence,is the most complex tissue in the human body.Brain diseases are among the leading threats to human life,yet our understanding of their pathogenic mechanisms and drug...Brain,the material foundation of human intelligence,is the most complex tissue in the human body.Brain diseases are among the leading threats to human life,yet our understanding of their pathogenic mechanisms and drug development remains limited,largely due to the lack of accurate brain-like tissue models that replicate its complex structure and functions.Therefore,constructing brain-like models—both in morphology and function—possesses significant scientific value for advancing brain science and pathological pharmacology research,representing the frontiers in the biomanufacturing field.This review outlines the primary requirements and challenges in biomanufacturing brain-like tissue,addressing its complex structures,functions,and environments.Also,the existing biomanufacturing technologies,strategies,and characteristics for brain-like models are depicted,and cutting-edge developments in biomanufacturing central neural repair prosthetics,brain development models,brain disease models,and brain-inspired biocomputing models are systematically reviewed.Finally,the paper concludes with future perspectives on the biomanufacturing of brain-like tissue transitioning from structural manufacturing to intelligent functioning.展开更多
Spiking neural networks(SNN)represent a paradigm shift toward discrete,event-driven neural computation that mirrors biological brain mechanisms.This survey systematically examines current SNN research,focusing on trai...Spiking neural networks(SNN)represent a paradigm shift toward discrete,event-driven neural computation that mirrors biological brain mechanisms.This survey systematically examines current SNN research,focusing on training methodologies,hardware implementations,and practical applications.We analyze four major training paradigms:ANN-to-SNN conversion,direct gradient-based training,spike-timing-dependent plasticity(STDP),and hybrid approaches.Our review encompasses major specialized hardware platforms:Intel Loihi,IBM TrueNorth,SpiNNaker,and BrainScaleS,analyzing their capabilities and constraints.We survey applications spanning computer vision,robotics,edge computing,and brain-computer interfaces,identifying where SNN provide compelling advantages.Our comparative analysis reveals SNN offer significant energy efficiency improvements(1000-10000×reduction)and natural temporal processing,while facing challenges in scalability and training complexity.We identify critical research directions including improved gradient estimation,standardized benchmarking protocols,and hardware-software co-design approaches.This survey provides researchers and practitioners with a comprehensive understanding of current SNN capabilities,limitations,and future prospects.展开更多
Neuromorphic computing has the potential to overcome limitations of traditional silicon technology in machine learning tasks.Recent advancements in large crossbar arrays and silicon-based asynchronous spiking neural n...Neuromorphic computing has the potential to overcome limitations of traditional silicon technology in machine learning tasks.Recent advancements in large crossbar arrays and silicon-based asynchronous spiking neural networks have led to promising neuromorphic systems.However,developing compact parallel computing technology for integrating artificial neural networks into traditional hardware remains a challenge.Organic computational materials offer affordable,biocompatible neuromorphic devices with exceptional adjustability and energy-efficient switching.Here,the review investigates the advancements made in the development of organic neuromorphic devices.This review explores resistive switching mechanisms such as interface-regulated filament growth,molecular-electronic dynamics,nanowire-confined filament growth,and vacancy-assisted ion migration,while proposing methodologies to enhance state retention and conductance adjustment.The survey examines the challenges faced in implementing low-power neuromorphic computing,e.g.,reducing device size and improving switching time.The review analyses the potential of these materials in adjustable,flexible,and low-power consumption applications,viz.biohybrid spiking circuits interacting with biological systems,systems that respond to specific events,robotics,intelligent agents,neuromorphic computing,neuromorphic bioelectronics,neuroscience,and other applications,and prospects of this technology.展开更多
Artificial intelligence (AI) is rapidly being applied to a wide range of fields,including medicine,and has been considered as an approach that may augment or substitute human professionals in primary healthcare.Howeve...Artificial intelligence (AI) is rapidly being applied to a wide range of fields,including medicine,and has been considered as an approach that may augment or substitute human professionals in primary healthcare.However,AI also raises several challenges and ethical concerns.In this article,the author investigates and discusses three aspects of AI in medicine and healthcare:the application and promises of AI,special ethical concerns pertaining to AI in some frontier fields,and suggestive ethical governance systems.Despite great potentials of frontier AI research and development in the field of medical care,the ethical challenges induced by its applications has put forward new requirements for governance.To ensure “trustworthy” AI applications in healthcare and medicine,the creation of an ethical global governance framework and system as well as special guidelines for frontier AI applications in medicine are suggested.The most important aspects include the roles of governments in ethical auditing and the responsibilities of stakeholders in the ethical governance system.展开更多
In the post-Moore era,neuromorphic computing has been mainly focused on breaking the von Neumann bottlenecks.Memristors have been proposed as a key part of neuromorphic computing architectures,and can be used to emula...In the post-Moore era,neuromorphic computing has been mainly focused on breaking the von Neumann bottlenecks.Memristors have been proposed as a key part of neuromorphic computing architectures,and can be used to emulate the synaptic plasticities of the human brain.Ferroelectric memristors represent a breakthrough for memristive devices on account of their reliable nonvolatile storage,low write/read latency and tunable conductive states.However,among the reported ferroelectric memristors,the mechanisms of resistive switching are still under debate.In addition,there needs to be more research on emulation of the brain synapses using ferroelectric memristors.Herein,Cu/PbZr_(0.52)Ti_(0.48)O_(3)(PZT)/Pt ferroelectric memristors have been fabricated.The devices are able to realize the transformation from threshold switching behavior to resistive switching behavior.The synaptic plasticities,including excitatory post-synaptic current,paired-pulse facilitation,paired-pulse depression and spike time-dependent plasticity,have been mimicked by the PZT devices.Furthermore,the mechanisms of PZT devices have been investigated by first-principles calculations based on the interface barrier and conductive filament models.This work may contribute to the application of ferroelectric memristors in neuromorphic computing systems.展开更多
Reproducing the spatial cognition of animals using computational models that make agents navigate autonomously has attracted much attention. Many biologically inspired models for spatial cognition focus mainly on the ...Reproducing the spatial cognition of animals using computational models that make agents navigate autonomously has attracted much attention. Many biologically inspired models for spatial cognition focus mainly on the simulation of the hippocampus and only consider the effect of external environmental information(i.e., exogenous information) on the hippocampal coding. However, neurophysiological studies have shown that the striatum, which is closely related to the hippocampus, also plays an important role in spatial cognition and that information inside animals(i.e., endogenous information) also affects the encoding of the hippocampus. Inspired by the progress made in neurophysiological studies, we propose a new spatial cognitive model that consists of analogies between the hippocampus and striatum. This model takes into consideration how both exogenous and endogenous information affects coding by the environment. We carried out a series of navigation experiments that simulated a water maze and compared our model with other models. Our model is self-adaptable and robust and has better performance in navigation path length. We also discuss the possible reasons for the results and how our findings may help us understand real mechanisms in the spatial cognition of animals.展开更多
Bayesian-based methods have emerged as an effective approach in continual learning(CL) to solve catastrophic forgetting. One prominent example is Variational Continual Learning(VCL), which demonstrates remarkable perf...Bayesian-based methods have emerged as an effective approach in continual learning(CL) to solve catastrophic forgetting. One prominent example is Variational Continual Learning(VCL), which demonstrates remarkable performance in task-incremental learning(task-IL).However, class-incremental learning(class-IL) is still challenging for VCL, and the reasons behind this limitation remain unclear. Relying on the sophisticated neural mechanisms, particularly the mechanism of memory consolidation during sleep, the human brain possesses inherent advantages for both task-IL and class-IL scenarios, which provides insight for a braininspired VCL. To identify the reasons for the inadequacy of VCL in class-IL, we first conduct a comprehensive theoretical analysis of VCL. On this basis, we propose a novel Bayesian framework named as Learning within Sleeping(Lw S) by leveraging the memory consolidation.By simulating the distribution integration and generalization observed during memory consolidation in sleep, Lw S achieves the idea of prior knowledge guiding posterior knowledge learning as in VCL. In addition, with emulating the process of memory reactivation of the brain,Lw S imposes a constraint on feature invariance to mitigate forgetting learned knowledge. Experimental results demonstrate that Lw S outperforms both Bayesian and non-Bayesian methods in task-IL and class-IL scenarios, which further indicates the effectiveness of incorporating brain mechanisms on designing novel approaches for CL.展开更多
基金Project supported by the National Natural Science Foundation of China(Grant No.61332003)High Performance Computing Laboratory,China(Grant No.201501-02)
文摘Memristors, as memristive devices, have received a great deal of interest since being fabricated by HP labs. The forgetting effect that has significant influences on memristors＇ performance has to be taken into account when they are employed. It is significant to build a good model that can express the forgetting effect well for application researches due to its promising prospects in brain-inspired computing. Some models are proposed to represent the forgetting effect but do not work well. In this paper, we present a novel window function, which has good performance in a drift model. We analyze the deficiencies of the previous drift diffusion models for the forgetting effect and propose an improved model. Moreover,the improved model is exploited as a synapse model in spiking neural networks to recognize digit images. Simulation results show that the improved model overcomes the defects of the previous models and can be used as a synapse model in brain-inspired computing due to its synaptic characteristics. The results also indicate that the improved model can express the forgetting effect better when it is employed in spiking neural networks, which means that more appropriate evaluations can be obtained in applications.
文摘By definition, bionics is the application of biological mechanisms found in nature to artificial systems in order to achieve specific functional goals. Successful examples range from Velcro, the touch fastener inspired by the hooks of burrs, to self-cleaning material, inspired by the surface of the lotus leaf. Recently, a new trend in bionics i Brain-Inspired Computing （BIC） - has captured increasing attention. Instead of learning from burrs and leaves, BIC aims to understand the brain and then utilize its operating principles to achieve powerful and efficient information processing.
基金supported by the General Program of National Natural Science Foundation of China(Grant No.61876021)the General Program of Beijing Natural Science Foundation(Grant No.4212037)。
文摘Recent advances in Artificial Intelligence(AI)have indicated that inspirations from the brain can effectively improve the level of intelligence for AI computational models,even if just local and partial inspirations.Nevertheless,realizing and exceeding intelligence at a human level still needs a deeper investigation and inspirations from the brain.The goal of brain-inspired intelligence is to achieve human intelligence inspired from brain neural mechanism and cognitive behavior mechanism.To this end,in this paper we introduce the relationship between AI and neuroscience,the current status of brain-inspired intelligence,the future work in intelligent control systems,and its profound influence in other fields.
基金supported in part by the National Nature Science Foundation of China(NSFC)under Grant No.62273229 and No.61873163.
文摘Recently,the brain-inspired mechanisms beneficial to efficient navigation in mammals have exhibited huge research potential.Specifically,the geometry cell model has shown significant insights into the ability of mammals,which is used to model the geometric information of their surroundings during movement.Meanwhile,the process of general exploration will consume large amounts of computing resources when agents with high-performance computing equipment accomplish autonomous tasks.This paper focuses on the long-range autonomous exploration and navigation tasks in which they are conducted by agents within complex indoor and outdoor environments.To reduce the computational demands,we propose a framework integrating the Brain-Inspired Geometry-awareness namely BIG for two autonomous tasks.The exploration task named BIG-Explorer involves efficiently searching untouched areas by embedding the geometry cell model.It identifies expanding frontiers using geometric assigners and takes into account relevant factors such as boundary information.The navigation task named BIG-Navigator builds upon insights gained during the exploration phase and guides agents to a predefined destination.We conduct comprehensive experimental assessments within third-party simulation environments.The evaluation metrics employed in this paper include the number of nodes,the length of a path,algorithm execution time,and the size of exploration space.Finally,the results of the evaluation demonstrate that the incorporation of geometry cell model increases the efficiency in both exploration and navigation processes by at least 20%,compared with four benchmark methods.
基金supported by the National Key R&D Program of China(No.2021YFC1809001).
文摘Efficiently predicting effluent quality through data-driven analysis presents a significant advancement for consistent wastewater treatment operations.In this study,we aimed to develop an integrated method for predicting effluent COD and NH3 levels.We employed a 200 L pilot-scale sequencing batch reactor(SBR)to gather multimodal data from urban sewage over 40 d.Then we collected data on critical parameters like COD,DO,pH,NH_(3),EC,ORP,SS,and water temperature,alongside wastewater surface images,resulting in a data set of approximately 40246 points.Then we proposed a brain-inspired image and temporal fusion model integrated with a CNN-LSTM network(BITF-CL)using this data.This innovative model synergized sewage imagery with water quality data,enhancing prediction accuracy.As a result,the BITF-CL model reduced prediction error by over 23%compared to traditional methods and still performed comparably to conventional techniques even without using DO and SS sensor data.Consequently,this research presents a cost-effective and precise prediction system for sewage treatment,demonstrating the potential of brain-inspired models.
基金This work was supported by the National Natural Science Foundation of China under Grant Nos.62250006,62072266,and 61836004the National Natural Science Foundation of China Youth Fund under Grant No.62202254,Beijing National Research Center for Information Science and Technology under Grant No.BNR2022RC01003+1 种基金the Tsinghua University Initiative Scientific Research Programthe Suzhou-Tsinghua Innovation Leadership Program.
文摘Brain-inspired computing is a new technology that draws on the principles of brain science and is oriented to the efficient development of artificial general intelligence(AGI),and a brain-inspired computing system is a hierarchical system composed of neuromorphic chips,basic software and hardware,and algorithms/applications that embody this tech-nology.While the system is developing rapidly,it faces various challenges and opportunities brought by interdisciplinary research,including the issue of software and hardware fragmentation.This paper analyzes the status quo of brain-inspired computing systems.Enlightened by some design principle and methodology of general-purpose computers,it is proposed to construct"general-purpose"brain-inspired computing systems.A general-purpose brain-inspired computing system refers to a brain-inspired computing hierarchy constructed based on the design philosophy of decoupling software and hardware,which can flexibly support various brain-inspired computing applications and neuromorphic chips with different architec-tures.Further,this paper introduces our recent work in these aspects,including the ANN(artificial neural network)/SNN(spiking neural network)development tools,the hardware agnostic compilation infrastructure,and the chip micro-archi-tecture with high flexibility of programming and high performance;these studies show that the"general-purpose"system can remarkably improve the efficiency of application development and enhance the productivity of basic software,thereby being conductive to accelerating the advancement of various brain-inspired algorithms and applications.We believe that this is the key to the collaborative research and development,and the evolution of applications,basic software and chips in this field,and conducive to building a favorable software/hardware ecosystem of brain-inspired computing.
基金the Special Zone Project of National Defense Innovation,the National Natural Science Foundation of China(Nos.61572304 and 61272096)the Key Program of the National Natural Science Foundation of China(No.61332019)Open Research Fund of State Key Laboratory of Cryptology。
文摘In recent years,the urbanization process has brought modernity while also causing key issues,such as traffic congestion and parking conflicts.Therefore,cities need a more intelligent"brain"to form more intelligent and efficient transportation systems.At present,as a type of machine learning,the traditional clustering algorithm still has limitations.K-means algorithm is widely used to solve traffic clustering problems,but it has limitations,such as sensitivity to initial points and poor robustness.Therefore,based on the hybrid architecture of Quantum Annealing(QA)and brain-inspired cognitive computing,this study proposes QA and Brain-Inspired Clustering Algorithm(QABICA)to solve the problem of urban taxi-stand locations.Based on the traffic trajectory data of Xi’an and Chengdu provided by Didi Chuxing,the clustering results of our algorithm and K-means algorithm are compared.We find that the average taxi-stand location bias of the final result based on QABICA is smaller than that based on K-means,and the bias of our algorithm can effectively reduce the tradition K-means bias by approximately 42%,up to approximately 83%,with higher robustness.QA algorithm is able to jump out of the local suboptimal solutions and approach the global optimum,and brain-inspired cognitive computing provides search feedback and direction.Thus,we will further consider applying our algorithm to analyze urban traffic flow,and solve traffic congestion and other key problems in intelligent transportation.
基金supported by National Natural Science Foundation of China(Nos.91948303,62203443 and 62203439)the Major Project of Science and Technology Innovation 2030 C Brain Science and Brain-inspired Intelligence(No.2021ZD0200408)+1 种基金the Strategic Priority Research Program of Chinese Academy of Science(No.XDB 32050100)the Science Foundation for Youth of the State Key Laboratory of Management and Control for Complex System(No.2022QN09).
文摘Traditional joint-link robots have been widely used in production lines because of their high precision for single tasks.With the development of the manufacturing and service industries,the requirement for the comprehensive performance of robotics is growing.Numerous types of bio-inspired robotics have been investigated to realize human-like motion control and manipulation.A study route from inner mechanisms to external structures is proposed to imitate humans and animals better.With this idea,a brain-inspired intelligent robotic system is constructed that contains visual cognition,decision-making,motion control,and musculoskeletal structures.This paper reviews cutting-edge research in brain-inspired visual cognition,decision-making,motion control,and musculoskeletal systems.Two software systems and a corresponding hardware system are established,aiming at the verification and applications of next-generationbrain-inspired musculoskeletal robots.
基金supported by National Key R&D Program of China(No.2020AAA0105200)Science and Technology Innovation 2030-Brain Science and Brain-inspired Intelligence Project(No.2021ZD0200204)+1 种基金National Key Research and Development Program of China(No.2020AAA0130401)Huawei Technology Co.,Ltd,China(No.YBN2019105137)。
文摘Brain-inspired computer vision aims to learn from biological systems to develop advanced image processing techniques.However,its progress so far is not impressing.We recognize that a main obstacle comes from that the current paradigm for brain-inspired computer vision has not captured the fundamental nature of biological vision,i.e.,the biological vision is targeted for processing spatio-temporal patterns.Recently,a new paradigm for developing brain-inspired computer vision is emerging,which emphasizes on the spatio-temporal nature of visual signals and the brain-inspired models for processing this type of data.In this paper,we review some recent primary works towards this new paradigm,including the development of spike cameras which acquire spiking signals directly from visual scenes,and the development of computational models learned from neural systems that are specialized to process spatio-temporal patterns,including models for object detection,tracking,and recognition.We also discuss about the future directions to improve the paradigm.
基金partly supported by the National Natural Science Foundation of China(Nos.62072266 and 62050340)Beijing Academy of Artificial Intelligence(No.BAAI2019ZD0403)。
文摘Brain-inspired computing refers to computational models,methods,and systems,that are mainly inspired by the processing mode or structure of brain.A recent study proposed the concept of"neuromorphic completeness"and the corresponding system hierarchy,which is helpful to determine the capability boundary of brain-inspired computing system and to judge whether hardware and software of brain-inspired computing are compatible with each other.As a position paper,this article analyzes the existing brain-inspired chips design characteristics and the current so-called"general purpose"application development frameworks for brain-inspired computing,as well as introduces the background and the potential of this proposal.Further,some key features of this concept are presented through the comparison with the Turing completeness and approximate computation,and the analyses of the relationship with"general-purpose"brain-inspired computing systems(it means that computing systems can support all computable applications).In the end,a promising technical approach to realize such computing systems is introduced,as well as the on-going research and the work foundation.We believe that this work is conducive to the design of extensible neuromorphic complete hardware-primitives and the corresponding chips.On this basis,it is expected to gradually realize"general purpose"brain-inspired computing system,in order to take into account the functionality completeness and application efficiency.
基金supported by National Key R&D Program of China(No.2018AAA0102600)Beijing Natural Science Foundation,China(No.JQ21015)+1 种基金Beijing Academy of Artificial Intelligence(BAAI),ChinaPengcheng Laboratory,China。
文摘Visual recognition is currently one of the most important and active research areas in computer vision,pattern recognition,and even the general field of artificial intelligence.It has great fundamental importance and strong industrial needs,particularly the modern deep neural networks(DNNs)and some brain-inspired methodologies,have largely boosted the recognition performance on many concrete tasks,with the help of large amounts of training data and new powerful computation resources.Although recognition accuracy is usually the first concern for new progresses,efficiency is actually rather important and sometimes critical for both academic research and industrial applications.Moreover,insightful views on the opportunities and challenges of efficiency are also highly required for the entire community.While general surveys on the efficiency issue have been done from various perspectives,as far as we are aware,scarcely any of them focused on visual recognition systematically,and thus it is unclear which progresses are applicable to it and what else should be concerned.In this survey,we present the review of recent advances with our suggestions on the new possible directions towards improving the efficiency of DNN-related and brain-inspired visual recognition approaches,including efficient network compression and dynamic brain-inspired networks.We investigate not only from the model but also from the data point of view(which is not the case in existing surveys)and focus on four typical data types(images,video,points,and events).This survey attempts to provide a systematic summary via a comprehensive survey that can serve as a valuable reference and inspire both researchers and practitioners working on visual recognition problems.
基金supported by National Natural Science Foundation of China(Grant Nos.61621136008,61327809,61210013,91420302,and 91520201)
文摘Modern computational models have leveraged biological advances in human brain research. This study addresses the problem of multimodal learning with the help of brain-inspired models. Specifically, a unified multimodal learning architecture is proposed based on deep neural networks, which are inspired by the biology of the visual cortex of the human brain. This unified framework is validated by two practical multimodal learning tasks: image captioning, involving visual and natural language signals, and visual-haptic fusion, involving haptic and visual signals. Extensive experiments are conducted under the framework, and competitive results are achieved.
基金supported by the Science and Technology Innovation 2030 Project of China(Nos.2021ZD02023501 and 2021ZD0202600)National Science Foundation of China(NSFC)(Nos.31970903,31671104,31371059 and 32225023)+1 种基金Shanghai Ministry of Science and Technology(No.19ZR1477400)NSFC and the German Research Foundation(DFG)in Project Crossmodal Learning(No.62061136001/TRR-169)。
文摘Despite its great success,deep learning severely suffers from robustness;i.e.,deep neural networks are very vulnerable to adversarial attacks,even the simplest ones.Inspired by recent advances in brain science,we propose the denoised internal models(DIM),a novel generative autoencoder-based model to tackle this challenge.Simulating the pipeline in the human brain for visual signal processing,DIM adopts a two-stage approach.In the first stage,DIM uses a denoiser to reduce the noise and the dimensions of inputs,reflecting the information pre-processing in the thalamus.Inspired by the sparse coding of memory-related traces in the primary visual cortex,the second stage produces a set of internal models,one for each category.We evaluate DIM over 42 adversarial attacks,showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness on the MNIST(Modified National Institute of Standards and Technology)dataset.
基金supported by the Program of the National Natural Science Foundation of China(52275291)(52435006)the Program for Innovation Team of Shaanxi Province(2023CX-TD-17)the Fundamental Research Funds for the Central Universities。
文摘Brain,the material foundation of human intelligence,is the most complex tissue in the human body.Brain diseases are among the leading threats to human life,yet our understanding of their pathogenic mechanisms and drug development remains limited,largely due to the lack of accurate brain-like tissue models that replicate its complex structure and functions.Therefore,constructing brain-like models—both in morphology and function—possesses significant scientific value for advancing brain science and pathological pharmacology research,representing the frontiers in the biomanufacturing field.This review outlines the primary requirements and challenges in biomanufacturing brain-like tissue,addressing its complex structures,functions,and environments.Also,the existing biomanufacturing technologies,strategies,and characteristics for brain-like models are depicted,and cutting-edge developments in biomanufacturing central neural repair prosthetics,brain development models,brain disease models,and brain-inspired biocomputing models are systematically reviewed.Finally,the paper concludes with future perspectives on the biomanufacturing of brain-like tissue transitioning from structural manufacturing to intelligent functioning.
文摘Spiking neural networks(SNN)represent a paradigm shift toward discrete,event-driven neural computation that mirrors biological brain mechanisms.This survey systematically examines current SNN research,focusing on training methodologies,hardware implementations,and practical applications.We analyze four major training paradigms:ANN-to-SNN conversion,direct gradient-based training,spike-timing-dependent plasticity(STDP),and hybrid approaches.Our review encompasses major specialized hardware platforms:Intel Loihi,IBM TrueNorth,SpiNNaker,and BrainScaleS,analyzing their capabilities and constraints.We survey applications spanning computer vision,robotics,edge computing,and brain-computer interfaces,identifying where SNN provide compelling advantages.Our comparative analysis reveals SNN offer significant energy efficiency improvements(1000-10000×reduction)and natural temporal processing,while facing challenges in scalability and training complexity.We identify critical research directions including improved gradient estimation,standardized benchmarking protocols,and hardware-software co-design approaches.This survey provides researchers and practitioners with a comprehensive understanding of current SNN capabilities,limitations,and future prospects.
基金financially supported by the Ministry of Education(Singapore)(MOE-T2EP50220-0022)SUTD-MIT International Design Center(Singapore)+3 种基金SUTD-ZJU IDEA Grant Program(SUTD-ZJU(VP)201903)SUTD Kickstarter Initiative(SKI 2021_02_03,SKI 2021_02_17,SKI 2021_01_04)Agency of Science,Technology and Research(Singapore)(A20G9b0135)National Supercomputing Centre(Singapore)(15001618)。
文摘Neuromorphic computing has the potential to overcome limitations of traditional silicon technology in machine learning tasks.Recent advancements in large crossbar arrays and silicon-based asynchronous spiking neural networks have led to promising neuromorphic systems.However,developing compact parallel computing technology for integrating artificial neural networks into traditional hardware remains a challenge.Organic computational materials offer affordable,biocompatible neuromorphic devices with exceptional adjustability and energy-efficient switching.Here,the review investigates the advancements made in the development of organic neuromorphic devices.This review explores resistive switching mechanisms such as interface-regulated filament growth,molecular-electronic dynamics,nanowire-confined filament growth,and vacancy-assisted ion migration,while proposing methodologies to enhance state retention and conductance adjustment.The survey examines the challenges faced in implementing low-power neuromorphic computing,e.g.,reducing device size and improving switching time.The review analyses the potential of these materials in adjustable,flexible,and low-power consumption applications,viz.biohybrid spiking circuits interacting with biological systems,systems that respond to specific events,robotics,intelligent agents,neuromorphic computing,neuromorphic bioelectronics,neuroscience,and other applications,and prospects of this technology.
文摘Artificial intelligence (AI) is rapidly being applied to a wide range of fields,including medicine,and has been considered as an approach that may augment or substitute human professionals in primary healthcare.However,AI also raises several challenges and ethical concerns.In this article,the author investigates and discusses three aspects of AI in medicine and healthcare:the application and promises of AI,special ethical concerns pertaining to AI in some frontier fields,and suggestive ethical governance systems.Despite great potentials of frontier AI research and development in the field of medical care,the ethical challenges induced by its applications has put forward new requirements for governance.To ensure “trustworthy” AI applications in healthcare and medicine,the creation of an ethical global governance framework and system as well as special guidelines for frontier AI applications in medicine are suggested.The most important aspects include the roles of governments in ethical auditing and the responsibilities of stakeholders in the ethical governance system.
基金Jiangsu Province Research Foundation(Grant Nos.BK20191202,RK106STP18003,and SZDG2018007)the Jiangsu Province Research Foundation(Grant Nos.BK20191202,RK106STP18003,and SZDG2018007)+1 种基金the Research Innovation Program for College Graduates of Jiangsu Province(Grant Nos.KYCX200806,KYCX190960,and SJCX190268)NJUPTSF(Grant Nos.NY217116,NY220078,and NY218107)。
文摘In the post-Moore era,neuromorphic computing has been mainly focused on breaking the von Neumann bottlenecks.Memristors have been proposed as a key part of neuromorphic computing architectures,and can be used to emulate the synaptic plasticities of the human brain.Ferroelectric memristors represent a breakthrough for memristive devices on account of their reliable nonvolatile storage,low write/read latency and tunable conductive states.However,among the reported ferroelectric memristors,the mechanisms of resistive switching are still under debate.In addition,there needs to be more research on emulation of the brain synapses using ferroelectric memristors.Herein,Cu/PbZr_(0.52)Ti_(0.48)O_(3)(PZT)/Pt ferroelectric memristors have been fabricated.The devices are able to realize the transformation from threshold switching behavior to resistive switching behavior.The synaptic plasticities,including excitatory post-synaptic current,paired-pulse facilitation,paired-pulse depression and spike time-dependent plasticity,have been mimicked by the PZT devices.Furthermore,the mechanisms of PZT devices have been investigated by first-principles calculations based on the interface barrier and conductive filament models.This work may contribute to the application of ferroelectric memristors in neuromorphic computing systems.
基金by National Natural Science Foundation of China(Nos.61773027 and 62076014)National Key Research and Development Program Project(No.2020YFB1005903)Industrial Internet Innovation and Development Project(No.135060009002).
文摘Reproducing the spatial cognition of animals using computational models that make agents navigate autonomously has attracted much attention. Many biologically inspired models for spatial cognition focus mainly on the simulation of the hippocampus and only consider the effect of external environmental information(i.e., exogenous information) on the hippocampal coding. However, neurophysiological studies have shown that the striatum, which is closely related to the hippocampus, also plays an important role in spatial cognition and that information inside animals(i.e., endogenous information) also affects the encoding of the hippocampus. Inspired by the progress made in neurophysiological studies, we propose a new spatial cognitive model that consists of analogies between the hippocampus and striatum. This model takes into consideration how both exogenous and endogenous information affects coding by the environment. We carried out a series of navigation experiments that simulated a water maze and compared our model with other models. Our model is self-adaptable and robust and has better performance in navigation path length. We also discuss the possible reasons for the results and how our findings may help us understand real mechanisms in the spatial cognition of animals.
基金supported by the National Natural Science Foundation of China under Grant 62236001 and Grant 62325601
文摘Bayesian-based methods have emerged as an effective approach in continual learning(CL) to solve catastrophic forgetting. One prominent example is Variational Continual Learning(VCL), which demonstrates remarkable performance in task-incremental learning(task-IL).However, class-incremental learning(class-IL) is still challenging for VCL, and the reasons behind this limitation remain unclear. Relying on the sophisticated neural mechanisms, particularly the mechanism of memory consolidation during sleep, the human brain possesses inherent advantages for both task-IL and class-IL scenarios, which provides insight for a braininspired VCL. To identify the reasons for the inadequacy of VCL in class-IL, we first conduct a comprehensive theoretical analysis of VCL. On this basis, we propose a novel Bayesian framework named as Learning within Sleeping(Lw S) by leveraging the memory consolidation.By simulating the distribution integration and generalization observed during memory consolidation in sleep, Lw S achieves the idea of prior knowledge guiding posterior knowledge learning as in VCL. In addition, with emulating the process of memory reactivation of the brain,Lw S imposes a constraint on feature invariance to mitigate forgetting learned knowledge. Experimental results demonstrate that Lw S outperforms both Bayesian and non-Bayesian methods in task-IL and class-IL scenarios, which further indicates the effectiveness of incorporating brain mechanisms on designing novel approaches for CL.
