Subjects -> COMPUTER SCIENCE (Total: 2313 journals)
    - ANIMATION AND SIMULATION (33 journals)
    - ARTIFICIAL INTELLIGENCE (133 journals)
    - AUTOMATION AND ROBOTICS (116 journals)
    - CLOUD COMPUTING AND NETWORKS (75 journals)
    - COMPUTER ARCHITECTURE (11 journals)
    - COMPUTER ENGINEERING (12 journals)
    - COMPUTER GAMES (23 journals)
    - COMPUTER PROGRAMMING (25 journals)
    - COMPUTER SCIENCE (1305 journals)
    - COMPUTER SECURITY (59 journals)
    - DATA BASE MANAGEMENT (21 journals)
    - DATA MINING (50 journals)
    - E-BUSINESS (21 journals)
    - E-LEARNING (30 journals)
    - ELECTRONIC DATA PROCESSING (23 journals)
    - IMAGE AND VIDEO PROCESSING (42 journals)
    - INFORMATION SYSTEMS (109 journals)
    - INTERNET (111 journals)
    - SOCIAL WEB (61 journals)
    - SOFTWARE (43 journals)
    - THEORY OF COMPUTING (10 journals)

COMPUTER SCIENCE (1305 journals)            First | 1 2 3 4 5 6 7 | Last

Showing 201 - 400 of 872 Journals sorted alphabetically
Computational Ecology and Software     Open Access   (Followers: 9)
Computational Economics     Hybrid Journal   (Followers: 12)
Computational Geosciences     Hybrid Journal   (Followers: 17)
Computational Linguistics     Open Access   (Followers: 23)
Computational Management Science     Hybrid Journal  
Computational Mathematics and Modeling     Hybrid Journal   (Followers: 8)
Computational Mechanics     Hybrid Journal   (Followers: 11)
Computational Methods and Function Theory     Hybrid Journal  
Computational Molecular Bioscience     Open Access   (Followers: 1)
Computational Optimization and Applications     Hybrid Journal   (Followers: 9)
Computational Particle Mechanics     Hybrid Journal   (Followers: 1)
Computational Science and Techniques     Open Access  
Computational Statistics     Hybrid Journal   (Followers: 15)
Computational Statistics & Data Analysis     Hybrid Journal   (Followers: 35)
Computational Toxicology     Hybrid Journal  
Computer     Full-text available via subscription   (Followers: 141)
Computer Aided Surgery     Open Access   (Followers: 5)
Computer Applications in Engineering Education     Hybrid Journal   (Followers: 6)
Computer Communications     Hybrid Journal   (Followers: 19)
Computer Engineering and Applications Journal     Open Access   (Followers: 8)
Computer Journal     Hybrid Journal   (Followers: 7)
Computer Methods in Applied Mechanics and Engineering     Hybrid Journal   (Followers: 25)
Computer Methods in Biomechanics and Biomedical Engineering     Hybrid Journal   (Followers: 10)
Computer Methods in Biomechanics and Biomedical Engineering : Imaging & Visualization     Hybrid Journal  
Computer Music Journal     Hybrid Journal   (Followers: 18)
Computer Physics Communications     Hybrid Journal   (Followers: 9)
Computer Science - Research and Development     Hybrid Journal   (Followers: 7)
Computer Science and Engineering     Open Access   (Followers: 15)
Computer Science and Information Technology     Open Access   (Followers: 12)
Computer Science Education     Hybrid Journal   (Followers: 15)
Computer Science Journal     Open Access   (Followers: 20)
Computer Science Review     Hybrid Journal   (Followers: 12)
Computer Standards & Interfaces     Hybrid Journal   (Followers: 3)
Computer Supported Cooperative Work (CSCW)     Hybrid Journal   (Followers: 8)
Computer-aided Civil and Infrastructure Engineering     Hybrid Journal   (Followers: 9)
Computer-Aided Design and Applications     Hybrid Journal   (Followers: 6)
Computers     Open Access   (Followers: 2)
Computers & Chemical Engineering     Hybrid Journal   (Followers: 12)
Computers & Education     Hybrid Journal   (Followers: 90)
Computers & Electrical Engineering     Hybrid Journal   (Followers: 8)
Computers & Geosciences     Hybrid Journal   (Followers: 30)
Computers & Mathematics with Applications     Full-text available via subscription   (Followers: 9)
Computers & Structures     Hybrid Journal   (Followers: 43)
Computers & Education Open     Open Access   (Followers: 2)
Computers & Industrial Engineering     Hybrid Journal   (Followers: 6)
Computers and Composition     Hybrid Journal   (Followers: 11)
Computers and Education: Artificial Intelligence     Open Access   (Followers: 2)
Computers and Electronics in Agriculture     Hybrid Journal   (Followers: 7)
Computers and Geotechnics     Hybrid Journal   (Followers: 12)
Computers in Biology and Medicine     Hybrid Journal   (Followers: 11)
Computers in Entertainment     Hybrid Journal  
Computers in Human Behavior Reports     Open Access  
Computers in Industry     Hybrid Journal   (Followers: 7)
Computers in the Schools     Hybrid Journal   (Followers: 8)
Computers, Environment and Urban Systems     Hybrid Journal   (Followers: 11)
Computerworld Magazine     Free   (Followers: 2)
Computing     Hybrid Journal   (Followers: 2)
Computing and Software for Big Science     Hybrid Journal   (Followers: 1)
Computing and Visualization in Science     Hybrid Journal   (Followers: 6)
Computing in Science & Engineering     Full-text available via subscription   (Followers: 31)
Computing Reviews     Full-text available via subscription   (Followers: 1)
Concurrency and Computation: Practice & Experience     Hybrid Journal  
Connection Science     Hybrid Journal  
Control Engineering Practice     Hybrid Journal   (Followers: 46)
Cryptologia     Hybrid Journal   (Followers: 3)
CSI Transactions on ICT     Hybrid Journal   (Followers: 2)
Cuadernos de Documentación Multimedia     Open Access  
Current Science     Open Access   (Followers: 115)
Cyber-Physical Systems     Hybrid Journal  
Cyberspace : Jurnal Pendidikan Teknologi Informasi     Open Access  
DAIMI Report Series     Open Access  
Data     Open Access   (Followers: 4)
Data & Policy     Open Access   (Followers: 3)
Data Science and Engineering     Open Access   (Followers: 6)
Data Technologies and Applications     Hybrid Journal   (Followers: 207)
Data-Centric Engineering     Open Access  
Datenbank-Spektrum     Hybrid Journal   (Followers: 1)
Datenschutz und Datensicherheit - DuD     Hybrid Journal  
Decision Analytics     Open Access   (Followers: 3)
Decision Support Systems     Hybrid Journal   (Followers: 13)
Design Journal : An International Journal for All Aspects of Design     Hybrid Journal   (Followers: 33)
Digital Biomarkers     Open Access   (Followers: 1)
Digital Chemical Engineering     Open Access  
Digital Chinese Medicine     Open Access  
Digital Creativity     Hybrid Journal   (Followers: 11)
Digital Experiences in Mathematics Education     Hybrid Journal   (Followers: 2)
Digital Finance : Smart Data Analytics, Investment Innovation, and Financial Technology     Hybrid Journal   (Followers: 3)
Digital Geography and Society     Open Access  
Digital Government : Research and Practice     Open Access   (Followers: 1)
Digital Health     Open Access   (Followers: 10)
Digital Journalism     Hybrid Journal   (Followers: 7)
Digital Medicine     Open Access   (Followers: 3)
Digital Platform: Information Technologies in Sociocultural Sphere     Open Access   (Followers: 1)
Digital Policy, Regulation and Governance     Hybrid Journal   (Followers: 2)
Digital War     Hybrid Journal   (Followers: 1)
Digitale Welt : Das Wirtschaftsmagazin zur Digitalisierung     Hybrid Journal  
Digitális Bölcsészet / Digital Humanities     Open Access   (Followers: 2)
Disaster Prevention and Management     Hybrid Journal   (Followers: 30)
Discours     Open Access   (Followers: 1)
Discourse & Communication     Hybrid Journal   (Followers: 26)
Discover Internet of Things     Open Access   (Followers: 2)
Discrete and Continuous Models and Applied Computational Science     Open Access  
Discrete Event Dynamic Systems     Hybrid Journal   (Followers: 3)
Discrete Mathematics & Theoretical Computer Science     Open Access   (Followers: 1)
Discrete Optimization     Full-text available via subscription   (Followers: 7)
Displays     Hybrid Journal  
Distributed and Parallel Databases     Hybrid Journal   (Followers: 2)
e-learning and education (eleed)     Open Access   (Followers: 39)
Ecological Indicators     Hybrid Journal   (Followers: 22)
Ecological Informatics     Hybrid Journal   (Followers: 3)
Ecological Management & Restoration     Hybrid Journal   (Followers: 15)
Ecosystems     Hybrid Journal   (Followers: 32)
Edu Komputika Journal     Open Access   (Followers: 1)
Education and Information Technologies     Hybrid Journal   (Followers: 53)
Educational Philosophy and Theory     Hybrid Journal   (Followers: 10)
Educational Psychology in Practice: theory, research and practice in educational psychology     Hybrid Journal   (Followers: 13)
Educational Research and Evaluation: An International Journal on Theory and Practice     Hybrid Journal   (Followers: 7)
Educational Theory     Hybrid Journal   (Followers: 9)
Egyptian Informatics Journal     Open Access   (Followers: 5)
Electronic Commerce Research and Applications     Hybrid Journal   (Followers: 5)
Electronic Design     Partially Free   (Followers: 125)
Electronic Letters on Computer Vision and Image Analysis     Open Access   (Followers: 10)
Elektron     Open Access  
Empirical Software Engineering     Hybrid Journal   (Followers: 8)
Energy for Sustainable Development     Hybrid Journal   (Followers: 13)
Engineering & Technology     Hybrid Journal   (Followers: 22)
Engineering Applications of Computational Fluid Mechanics     Open Access   (Followers: 23)
Engineering Computations     Hybrid Journal   (Followers: 3)
Engineering Economist, The     Hybrid Journal   (Followers: 4)
Engineering Optimization     Hybrid Journal   (Followers: 19)
Engineering With Computers     Hybrid Journal   (Followers: 5)
Enterprise Information Systems     Hybrid Journal   (Followers: 2)
Entertainment Computing     Hybrid Journal   (Followers: 2)
Environmental and Ecological Statistics     Hybrid Journal   (Followers: 7)
Environmental Communication: A Journal of Nature and Culture     Hybrid Journal   (Followers: 16)
EPJ Data Science     Open Access   (Followers: 10)
ESAIM: Control Optimisation and Calculus of Variations     Open Access   (Followers: 2)
Ethics and Information Technology     Hybrid Journal   (Followers: 64)
eTransportation     Open Access   (Followers: 1)
EURO Journal on Computational Optimization     Open Access   (Followers: 5)
EuroCALL Review     Open Access  
European Food Research and Technology     Hybrid Journal   (Followers: 8)
European Journal of Combinatorics     Full-text available via subscription   (Followers: 3)
European Journal of Computational Mechanics     Hybrid Journal   (Followers: 1)
European Journal of Information Systems     Hybrid Journal   (Followers: 85)
European Journal of Law and Technology     Open Access   (Followers: 18)
European Journal of Political Theory     Hybrid Journal   (Followers: 27)
Evolutionary Computation     Hybrid Journal   (Followers: 11)
Fibreculture Journal     Open Access   (Followers: 9)
Finite Fields and Their Applications     Full-text available via subscription   (Followers: 5)
Fixed Point Theory and Applications     Open Access  
Focus on Catalysts     Full-text available via subscription  
Focus on Pigments     Full-text available via subscription   (Followers: 3)
Focus on Powder Coatings     Full-text available via subscription   (Followers: 5)
Forensic Science International: Digital Investigation     Full-text available via subscription   (Followers: 317)
Formal Aspects of Computing     Hybrid Journal   (Followers: 3)
Formal Methods in System Design     Hybrid Journal   (Followers: 6)
Forschung     Hybrid Journal   (Followers: 1)
Foundations and Trends® in Communications and Information Theory     Full-text available via subscription   (Followers: 6)
Foundations and Trends® in Databases     Full-text available via subscription   (Followers: 2)
Foundations and Trends® in Human-Computer Interaction     Full-text available via subscription   (Followers: 5)
Foundations and Trends® in Information Retrieval     Full-text available via subscription   (Followers: 30)
Foundations and Trends® in Networking     Full-text available via subscription   (Followers: 1)
Foundations and Trends® in Signal Processing     Full-text available via subscription   (Followers: 7)
Foundations and Trends® in Theoretical Computer Science     Full-text available via subscription   (Followers: 1)
Foundations of Computational Mathematics     Hybrid Journal  
Foundations of Computing and Decision Sciences     Open Access  
Frontiers in Computational Neuroscience     Open Access   (Followers: 23)
Frontiers in Computer Science     Open Access   (Followers: 1)
Frontiers in Digital Health     Open Access   (Followers: 4)
Frontiers in Digital Humanities     Open Access   (Followers: 7)
Frontiers in ICT     Open Access  
Frontiers in Neuromorphic Engineering     Open Access   (Followers: 2)
Frontiers in Research Metrics and Analytics     Open Access   (Followers: 4)
Frontiers of Computer Science in China     Hybrid Journal   (Followers: 2)
Frontiers of Environmental Science & Engineering     Hybrid Journal   (Followers: 3)
Frontiers of Information Technology & Electronic Engineering     Hybrid Journal  
Fuel Cells Bulletin     Full-text available via subscription   (Followers: 9)
Functional Analysis and Its Applications     Hybrid Journal   (Followers: 3)
Future Computing and Informatics Journal     Open Access  
Future Generation Computer Systems     Hybrid Journal   (Followers: 2)
Geo-spatial Information Science     Open Access   (Followers: 7)
Geoforum Perspektiv     Open Access  
GeoInformatica     Hybrid Journal   (Followers: 7)
Geoinformatics FCE CTU     Open Access   (Followers: 8)
GetMobile : Mobile Computing and Communications     Full-text available via subscription   (Followers: 1)
Government Information Quarterly     Hybrid Journal   (Followers: 28)
Granular Computing     Hybrid Journal  
Graphics and Visual Computing     Open Access  
Grey Room     Hybrid Journal   (Followers: 16)
Group Dynamics : Theory, Research, and Practice     Full-text available via subscription   (Followers: 15)
Groups, Complexity, Cryptology     Open Access   (Followers: 2)
HardwareX     Open Access  
Harvard Data Science Review     Open Access   (Followers: 3)
Health Services Management Research     Hybrid Journal   (Followers: 16)
Healthcare Technology Letters     Open Access  
High Frequency     Hybrid Journal  
High-Confidence Computing     Open Access   (Followers: 1)
Home Cultures     Full-text available via subscription   (Followers: 7)
Home Health Care Management & Practice     Hybrid Journal   (Followers: 1)

  First | 1 2 3 4 5 6 7 | Last

Similar Journals
Journal Cover
Frontiers in Neuromorphic Engineering
Number of Followers: 2  

  This is an Open Access Journal Open Access journal
ISSN (Online) 1662-453X
Published by Frontiers Media Homepage  [96 journals]
  • Parallelization of Neural Processing on Neuromorphic Hardware

    • Authors: Luca Peres, Oliver Rhodes
      Abstract: Learning and development in real brains typically happens over long timescales, making long-term exploration of these features a significant research challenge. One way to address this problem is to use computational models to explore the brain, with Spiking Neural Networks a popular choice to capture neuron and synapse dynamics. However, researchers require simulation tools and platforms to execute simulations in real- or sub-realtime, to enable exploration of features such as long-term learning and neural pathologies over meaningful periods. This article presents novel multicore processing strategies on the SpiNNaker Neuromorphic hardware, addressing parallelization of Spiking Neural Network operations through allocation of dedicated computational units to specific tasks (such as neural and synaptic processing) to optimize performance. The work advances previous real-time simulations of a cortical microcircuit model, parameterizing load balancing between computational units in order to explore trade-offs between computational complexity and speed, to provide the best fit for a given application. By exploiting the flexibility of the SpiNNaker Neuromorphic platform, up to 9× throughput of neural operations is demonstrated when running biologically representative Spiking Neural Networks.
      PubDate: 2022-05-10T00:00:00Z
       
  • Heterogeneous Ensemble-Based Spike-Driven Few-Shot Online Learning

    • Authors: Shuangming Yang, Bernabe Linares-Barranco, Badong Chen
      Abstract: Spiking neural networks (SNNs) are regarded as a promising candidate to deal with the major challenges of current machine learning techniques, including the high energy consumption induced by deep neural networks. However, there is still a great gap between SNNs and the few-shot learning performance of artificial neural networks. Importantly, existing spike-based few-shot learning models do not target robust learning based on spatiotemporal dynamics and superior machine learning theory. In this paper, we propose a novel spike-based framework with the entropy theory, namely, heterogeneous ensemble-based spike-driven few-shot online learning (HESFOL). The proposed HESFOL model uses the entropy theory to establish the gradient-based few-shot learning scheme in a recurrent SNN architecture. We examine the performance of the HESFOL model based on the few-shot classification tasks using spiking patterns and the Omniglot data set, as well as the few-shot motor control task using an end-effector. Experimental results show that the proposed HESFOL scheme can effectively improve the accuracy and robustness of spike-driven few-shot learning performance. More importantly, the proposed HESFOL model emphasizes the application of modern entropy-based machine learning methods in state-of-the-art spike-driven learning algorithms. Therefore, our study provides new perspectives for further integration of advanced entropy theory in machine learning to improve the learning performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic systems.
      PubDate: 2022-05-09T00:00:00Z
       
  • Real-Time Event-Based Unsupervised Feature Consolidation and Tracking for
           Space Situational Awareness

    • Authors: Nicholas Ralph, Damien Joubert, Andrew Jolley, Saeed Afshar, Nicholas Tothill, André van Schaik, Gregory Cohen
      Abstract: Earth orbit is a limited natural resource that hosts a vast range of vital space-based systems that support the international community's national, commercial and defence interests. This resource is rapidly becoming depleted with over-crowding in high demand orbital slots and a growing presence of space debris. We propose the Fast Iterative Extraction of Salient targets for Tracking Asynchronously (FIESTA) algorithm as a robust, real-time and reactive approach to optical Space Situational Awareness (SSA) using Event-Based Cameras (EBCs) to detect, localize, and track Resident Space Objects (RSOs) accurately and timely. We address the challenges of the asynchronous nature and high temporal resolution output of the EBC accurately, unsupervised and with few tune-able parameters using concepts established in the neuromorphic and conventional tracking literature. We show this algorithm is capable of highly accurate in-frame RSO velocity estimation and average sub-pixel localization in a simulated test environment to distinguish the capabilities of the EBC and optical setup from the proposed tracking system. This work is a fundamental step toward accurate end-to-end real-time optical event-based SSA, and developing the foundation for robust closed-form tracking evaluated using standardized tracking metrics.
      PubDate: 2022-05-06T00:00:00Z
       
  • Memristive Izhikevich Spiking Neuron Model and Its Application in
           Oscillatory Associative Memory

    • Authors: Xiaoyan Fang, Shukai Duan, Lidan Wang
      Abstract: The Izhikevich (IZH) spiking neuron model can display spiking and bursting behaviors of neurons. Based on the switching property and bio-plausibility of the memristor, the memristive Izhikevich (MIZH) spiking neuron model is built. Firstly, the MIZH spiking model is introduced and used to generate 23 spiking patterns. We compare the 23 spiking patterns produced by the IZH and MIZH spiking models. Secondly, the MIZH spiking model actively reproduces various neuronal behaviors, including the excitatory cortical neurons, the inhibitory cortical neurons, and other cortical neurons. Finally, the collective dynamic activities of the MIZH neuronal network are performed, and the MIZH oscillatory network is constructed. Experimental results illustrate that the constructed MIZH spiking neuron model performs high firing frequency and good frequency adaptation. The model can easily simulate various spiking and bursting patterns of distinct neurons in the brain. The MIZH neuronal network realizes the synchronous and asynchronous collective behaviors. The MIZH oscillatory network can memorize and retrieve the information patterns correctly and efficiently with high retrieval accuracy.
      PubDate: 2022-05-03T00:00:00Z
       
  • Modeling the Repetition-Based Recovering of Acoustic and Visual Sources
           With Dendritic Neurons

    • Authors: Giorgia Dellaferrera, Toshitake Asabuki, Tomoki Fukai
      Abstract: In natural auditory environments, acoustic signals originate from the temporal superimposition of different sound sources. The problem of inferring individual sources from ambiguous mixtures of sounds is known as blind source decomposition. Experiments on humans have demonstrated that the auditory system can identify sound sources as repeating patterns embedded in the acoustic input. Source repetition produces temporal regularities that can be detected and used for segregation. Specifically, listeners can identify sounds occurring more than once across different mixtures, but not sounds heard only in a single mixture. However, whether such a behavior can be computationally modeled has not yet been explored. Here, we propose a biologically inspired computational model to perform blind source separation on sequences of mixtures of acoustic stimuli. Our method relies on a somatodendritic neuron model trained with a Hebbian-like learning rule which was originally conceived to detect spatio-temporal patterns recurring in synaptic inputs. We show that the segregation capabilities of our model are reminiscent of the features of human performance in a variety of experimental settings involving synthesized sounds with naturalistic properties. Furthermore, we extend the study to investigate the properties of segregation on task settings not yet explored with human subjects, namely natural sounds and images. Overall, our work suggests that somatodendritic neuron models offer a promising neuro-inspired learning strategy to account for the characteristics of the brain segregation capabilities as well as to make predictions on yet untested experimental settings.
      PubDate: 2022-04-28T00:00:00Z
       
  • Neuroevolution Guided Hybrid Spiking Neural Network Training

    • Authors: Sen Lu, Abhronil Sengupta
      Abstract: Neuromorphic computing algorithms based on Spiking Neural Networks (SNNs) are evolving to be a disruptive technology driving machine learning research. The overarching goal of this work is to develop a structured algorithmic framework for SNN training that optimizes unique SNN-specific properties like neuron spiking threshold using neuroevolution as a feedback strategy. We provide extensive results for this hybrid bio-inspired training strategy and show that such a feedback-based learning approach leads to explainable neuromorphic systems that adapt to the specific underlying application. Our analysis reveals 53.8, 28.8, and 28.2% latency improvement for the neuroevolution-based SNN training strategy on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively in contrast to state-of-the-art conversion based approaches. The proposed algorithm can be easily extended to other application domains like image classification in presence of adversarial attacks where 43.2 and 27.9% latency improvements were observed on CIFAR-10 and CIFAR-100 datasets, respectively.
      PubDate: 2022-04-25T00:00:00Z
       
  • SAM: A Unified Self-Adaptive Multicompartmental Spiking Neuron Model for
           Learning With Working Memory

    • Authors: Shuangming Yang, Tian Gao, Jiang Wang, Bin Deng, Mostafa Rahimi Azghadi, Tao Lei, Bernabe Linares-Barranco
      Abstract: Working memory is a fundamental feature of biological brains for perception, cognition, and learning. In addition, learning with working memory, which has been show in conventional artificial intelligence systems through recurrent neural networks, is instrumental to advanced cognitive intelligence. However, it is hard to endow a simple neuron model with working memory, and to understand the biological mechanisms that have resulted in such a powerful ability at the neuronal level. This article presents a novel self-adaptive multicompartment spiking neuron model, referred to as SAM, for spike-based learning with working memory. SAM integrates four major biological principles including sparse coding, dendritic non-linearity, intrinsic self-adaptive dynamics, and spike-driven learning. We first describe SAM’s design and explore the impacts of critical parameters on its biological dynamics. We then use SAM to build spiking networks to accomplish several different tasks including supervised learning of the MNIST dataset using sequential spatiotemporal encoding, noisy spike pattern classification, sparse coding during pattern classification, spatiotemporal feature detection, meta-learning with working memory applied to a navigation task and the MNIST classification task, and working memory for spatiotemporal learning. Our experimental results highlight the energy efficiency and robustness of SAM in these wide range of challenging tasks. The effects of SAM model variations on its working memory are also explored, hoping to offer insight into the biological mechanisms underlying working memory in the brain. The SAM model is the first attempt to integrate the capabilities of spike-driven learning and working memory in a unified single neuron with multiple timescale dynamics. The competitive performance of SAM could potentially contribute to the development of efficient adaptive neuromorphic computing systems for various applications from robotics to edge computing.
      PubDate: 2022-04-18T00:00:00Z
       
  • Backpropagation With Sparsity Regularization for Spiking Neural Network
           Learning

    • Authors: Yulong Yan, Haoming Chu, Yi Jin, Yuxiang Huan, Zhuo Zou, Lirong Zheng
      Abstract: The spiking neural network (SNN) is a possible pathway for low-power and energy-efficient processing and computing exploiting spiking-driven and sparsity features of biological systems. This article proposes a sparsity-driven SNN learning algorithm, namely backpropagation with sparsity regularization (BPSR), aiming to achieve improved spiking and synaptic sparsity. Backpropagation incorporating spiking regularization is utilized to minimize the spiking firing rate with guaranteed accuracy. Backpropagation realizes the temporal information capture and extends to the spiking recurrent layer to support brain-like structure learning. The rewiring mechanism with synaptic regularization is suggested to further mitigate the redundancy of the network structure. Rewiring based on weight and gradient regulates the pruning and growth of synapses. Experimental results demonstrate that the network learned by BPSR has synaptic sparsity and is highly similar to the biological system. It not only balances the accuracy and firing rate, but also facilitates SNN learning by suppressing the information redundancy. We evaluate the proposed BPSR on the visual dataset MNIST, N-MNIST, and CIFAR10, and further test it on the sensor dataset MIT-BIH and gas sensor. Results bespeak that our algorithm achieves comparable or superior accuracy compared to related works, with sparse spikes and synapses.
      PubDate: 2022-04-14T00:00:00Z
       
  • A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety
           Risks of Other Agents

    • Authors: Zhuoya Zhao, Enmeng Lu, Feifei Zhao, Yi Zeng, Yuxuan Zhao
      Abstract: Artificial Intelligence (AI) systems are increasingly applied to complex tasks that involve interaction with multiple agents. Such interaction-based systems can lead to safety risks. Due to limited perception and prior knowledge, agents acting in the real world may unconsciously hold false beliefs and strategies about their environment, leading to safety risks in their future decisions. For humans, we can usually rely on the high-level theory of mind (ToM) capability to perceive the mental states of others, identify risk-inducing errors, and offer our timely help to keep others away from dangerous situations. Inspired by the biological information processing mechanism of ToM, we propose a brain-inspired theory of mind spiking neural network (ToM-SNN) model to enable agents to perceive such risk-inducing errors inside others' mental states and make decisions to help others when necessary. The ToM-SNN model incorporates the multiple brain areas coordination mechanisms and biologically realistic spiking neural networks (SNNs) trained with Reward-modulated Spike-Timing-Dependent Plasticity (R-STDP). To verify the effectiveness of the ToM-SNN model, we conducted various experiments in the gridworld environments with random agents' starting positions and random blocking walls. Experimental results demonstrate that the agent with the ToM-SNN model selects rescue behavior to help others avoid safety risks based on self-experience and prior knowledge. To the best of our knowledge, this study provides a new perspective to explore how agents help others avoid potential risks based on bio-inspired ToM mechanisms and may contribute more inspiration toward better research on safety risks.
      PubDate: 2022-04-14T00:00:00Z
       
  • Voltage–Time Transformation Model for Threshold Switching Spiking Neuron
           Based on Nucleation Theory

    • Authors: Suk-Min Yap, I-Ting Wang, Ming-Hung Wu, Tuo-Hung Hou
      Abstract: In this study, we constructed a voltage–time transformation model (V–t Model) to predict and simulate the spiking behavior of threshold-switching selector-based neurons (TS neurons). The V–t Model combines the physical nucleation theory and the resistor–capacitor (RC) equivalent circuit and successfully depicts the history-dependent threshold voltage of TS selectors, which has not yet been modeled in TS neurons. Moreover, based on our model, we analyzed the currently reported TS devices, including ovonic threshold switching (OTS), insulator-metal transition, and silver- (Ag-) based selectors, and compared the behaviors of the predicted neurons. The results suggest that the OTS neuron is the most promising and potentially achieves the highest spike frequency of GHz and the lowest operating voltage and area overhead. The proposed V–t Model provides an engineering pathway toward the future development of TS neurons for neuromorphic computing applications.
      PubDate: 2022-04-13T00:00:00Z
       
  • MONETA: A Processing-In-Memory-Based Hardware Platform for the Hybrid
           Convolutional Spiking Neural Network With Online Learning

    • Authors: Daehyun Kim, Biswadeep Chakraborty, Xueyuan She, Edward Lee, Beomseok Kang, Saibal Mukhopadhyay
      Abstract: We present a processing-in-memory (PIM)-based hardware platform, referred to as MONETA, for on-chip acceleration of inference and learning in hybrid convolutional spiking neural network. MONETAuses 8T static random-access memory (SRAM)-based PIM cores for vector matrix multiplication (VMM) augmented with spike-time-dependent-plasticity (STDP) based weight update. The spiking neural network (SNN)-focused data flow is presented to minimize data movement in MONETAwhile ensuring learning accuracy. MONETAsupports on-line and on-chip training on PIM architecture. The STDP-trained convolutional neural network within SNN (ConvSNN) with the proposed data flow, 4-bit input precision, and 8-bit weight precision shows only 1.63% lower accuracy in CIFAR-10 compared to the STDP accuracy implemented by the software. Further, the proposed architecture is used to accelerate a hybrid SNN architecture that couples off-chip supervised (back propagation through time) and on-chip unsupervised (STDP) training. We also evaluate the hybrid network architecture with the proposed data flow. The accuracy of this hybrid network is 10.84% higher than STDP trained accuracy result and 1.4% higher compared to the backpropagated training-based ConvSNN result with the CIFAR-10 dataset. Physical design of MONETAin 65 nm complementary metal-oxide-semiconductor (CMOS) shows 18.69 tera operation per second (TOPS)/W, 7.25 TOPS/W and 10.41 TOPS/W power efficiencies for the inference mode, learning mode, and hybrid learning mode, respectively.
      PubDate: 2022-04-11T00:00:00Z
       
  • Memristive LIF Spiking Neuron Model and Its Application in Morse Code

    • Authors: Xiaoyan Fang, Derong Liu, Shukai Duan, Lidan Wang
      Abstract: The leaky integrate-and-fire (LIF) spiking model can successively mimic the firing patterns and information propagation of a biological neuron. It has been applied in neural networks, cognitive computing, and brain-inspired computing. Due to the resistance variability and the natural storage capacity of the memristor, the LIF spiking model with a memristor (MLIF) is presented in this article to simulate the function and working mode of neurons in biological systems. First, the comparison between the MLIF spiking model and the LIF spiking model is conducted. Second, it is experimentally shown that a single memristor could mimic the function of the integration and filtering of the dendrite and emulate the function of the integration and firing of the soma. Finally, the feasibility of the proposed MLIF spiking model is verified by the generation and recognition of Morse code. The experimental results indicate that the presented MLIF model efficiently performs good biological frequency adaptation, high firing frequency, and rich spiking patterns. A memristor can be used as the dendrite and the soma, and the MLIF spiking model can emulate the axon. The constructed single neuron can efficiently complete the generation and propagation of firing patterns.
      PubDate: 2022-04-07T00:00:00Z
       
  • ACE-SNN: Algorithm-Hardware Co-design of Energy-Efficient & Low-Latency
           Deep Spiking Neural Networks for 3D Image Recognition

    • Authors: Gourav Datta, Souvik Kundu, Akhilesh R. Jaiswal, Peter A. Beerel
      Abstract: High-quality 3D image recognition is an important component of many vision and robotics systems. However, the accurate processing of these images requires the use of compute-expensive 3D Convolutional Neural Networks (CNNs). To address this challenge, we propose the use of Spiking Neural Networks (SNNs) that are generated from iso-architecture CNNs and trained with quantization-aware gradient descent to optimize their weights, membrane leak, and firing thresholds. During both training and inference, the analog pixel values of a 3D image are directly applied to the input layer of the SNN without the need to convert to a spike-train. This significantly reduces the training and inference latency and results in high degree of activation sparsity, which yields significant improvements in computational efficiency. However, this introduces energy-hungry digital multiplications in the first layer of our models, which we propose to mitigate using a processing-in-memory (PIM) architecture. To evaluate our proposal, we propose a 3D and a 3D/2D hybrid SNN-compatible convolutional architecture and choose hyperspectral imaging (HSI) as an application for 3D image recognition. We achieve overall test accuracy of 98.68, 99.50, and 97.95% with 5 time steps (inference latency) and 6-bit weight quantization on the Indian Pines, Pavia University, and Salinas Scene datasets, respectively. In particular, our models implemented using standard digital hardware achieved accuracies similar to state-of-the-art (SOTA) with ~560.6× and ~44.8× less average energy than an iso-architecture full-precision and 6-bit quantized CNN, respectively. Adopting the PIM architecture in the first layer, further improves the average energy, delay, and energy-delay-product (EDP) by 30, 7, and 38%, respectively.
      PubDate: 2022-04-07T00:00:00Z
       
  • Automotive Radar Processing With Spiking Neural Networks: Concepts and
           Challenges

    • Authors: Bernhard Vogginger, Felix Kreutz, Javier López-Randulfe, Chen Liu, Robin Dietrich, Hector A. Gonzalez, Daniel Scholz, Nico Reeb, Daniel Auge, Julian Hille, Muhammad Arsalan, Florian Mirus, Cyprian Grassmann, Alois Knoll, Christian Mayr
      Abstract: Frequency-modulated continuous wave radar sensors play an essential role for assisted and autonomous driving as they are robust under all weather and light conditions. However, the rising number of transmitters and receivers for obtaining a higher angular resolution increases the cost for digital signal processing. One promising approach for energy-efficient signal processing is the usage of brain-inspired spiking neural networks (SNNs) implemented on neuromorphic hardware. In this article we perform a step-by-step analysis of automotive radar processing and argue how spiking neural networks could replace or complement the conventional processing. We provide SNN examples for two processing steps and evaluate their accuracy and computational efficiency. For radar target detection, an SNN with temporal coding is competitive to the conventional approach at a low compute overhead. Instead, our SNN for target classification achieves an accuracy close to a reference artificial neural network while requiring 200 times less operations. Finally, we discuss the specific requirements and challenges for SNN-based radar processing on neuromorphic hardware. This study proves the general applicability of SNNs for automotive radar processing and sustains the prospect of energy-efficient realizations in automated vehicles.
      PubDate: 2022-04-01T00:00:00Z
       
  • Editorial: Emerging Technologies and Systems for Biologically Plausible
           Implementations of Neural Functions

    • Authors: Erika Covi, Elisa Donati, Stefano Brivio, Hadi Heidari
      PubDate: 2022-03-31T00:00:00Z
       
  • ALSA: Associative Learning Based Supervised Learning Algorithm for SNN

    • Authors: Lingfei Mo, Gang Wang, Erhong Long, Mingsong Zhuo
      Abstract: Spiking neural network (SNN) is considered to be the brain-like model that best conforms to the biological mechanism of the brain. Due to the non-differentiability of the spike, the training method of SNNs is still incomplete. This paper proposes a supervised learning method for SNNs based on associative learning: ALSA. The method is based on the associative learning mechanism, and its realization is similar to the animal conditioned reflex process, with strong physiological plausibility and rationality. This method uses improved spike-timing-dependent plasticity (STDP) rules, combined with a teacher layer to induct spikes of neurons, to strengthen synaptic connections between input spike patterns and specified output neurons, and weaken synaptic connections between unrelated patterns and unrelated output neurons. Based on ALSA, this paper also completed the supervised learning classification tasks of the IRIS dataset and the MNIST dataset, and achieved 95.7 and 91.58% recognition accuracy, respectively, which fully proves that ALSA is a feasible SNNs supervised learning method. The innovation of this paper is to establish a biological plausible supervised learning method for SNNs, which is based on the STDP learning rules and the associative learning mechanism that exists widely in animal training.
      PubDate: 2022-03-31T00:00:00Z
       
  • Liquid State Machine on SpiNNaker for Spatio-Temporal Classification Tasks

    • Authors: Alberto Patiño-Saucedo, Horacio Rostro-González, Teresa Serrano-Gotarredona, Bernabé Linares-Barranco
      Abstract: Liquid State Machines (LSMs) are computing reservoirs composed of recurrently connected Spiking Neural Networks which have attracted research interest for their modeling capacity of biological structures and as promising pattern recognition tools suitable for their implementation in neuromorphic processors, benefited from the modest use of computing resources in their training process. However, it has been difficult to optimize LSMs for solving complex tasks such as event-based computer vision and few implementations in large-scale neuromorphic processors have been attempted. In this work, we show that offline-trained LSMs implemented in the SpiNNaker neuromorphic processor are able to classify visual events, achieving state-of-the-art performance in the event-based N-MNIST dataset. The training of the readout layer is performed using a recent adaptation of back-propagation-through-time (BPTT) for SNNs, while the internal weights of the reservoir are kept static. Results show that mapping our LSM from a Deep Learning framework to SpiNNaker does not affect the performance of the classification task. Additionally, we show that weight quantization, which substantially reduces the memory footprint of the LSM, has a small impact on its performance.
      PubDate: 2022-03-14T00:00:00Z
       
  • Periodicity Pitch Perception Part III: Sensibility and Pachinko Volatility

    • Authors: Frank Feldhoff, Hannes Toepfer, Tamas Harczos, Frank Klefenz
      Abstract: Neuromorphic computer models are used to explain sensory perceptions. Auditory models generate cochleagrams, which resemble the spike distributions in the auditory nerve. Neuron ensembles along the auditory pathway transform sensory inputs step by step and at the end pitch is represented in auditory categorical spaces. In two previous articles in the series on periodicity pitch perception an extended auditory model had been successfully used for explaining periodicity pitch proved for various musical instrument generated tones and sung vowels. In this third part in the series the focus is on octopus cells as they are central sensitivity elements in auditory cognition processes. A powerful numerical model had been devised, in which auditory nerve fibers (ANFs) spike events are the inputs, triggering the impulse responses of the octopus cells. Efficient algorithms are developed and demonstrated to explain the behavior of octopus cells with a focus on a simple event-based hardware implementation of a layer of octopus neurons. The main finding is, that an octopus' cell model in a local receptive field fine-tunes to a specific trajectory by a spike-timing-dependent plasticity (STDP) learning rule with synaptic pre-activation and the dendritic back-propagating signal as post condition. Successful learning explains away the teacher and there is thus no need for a temporally precise control of plasticity that distinguishes between learning and retrieval phases. Pitch learning is cascaded: At first octopus cells respond individually by self-adjustment to specific trajectories in their local receptive fields, then unions of octopus cells are collectively learned for pitch discrimination. Pitch estimation by inter-spike intervals is shown exemplary using two input scenarios: a simple sinus tone and a sung vowel. The model evaluation indicates an improvement in pitch estimation on a fixed time-scale.
      PubDate: 2022-03-08T00:00:00Z
       
  • A Unified Software/Hardware Scalable Architecture for Brain-Inspired
           Computing Based on Self-Organizing Neural Models

    • Authors: Artem R. Muliukov, Laurent Rodriguez, Benoit Miramond, Lyes Khacef, Joachim Schmidt, Quentin Berthet, Andres Upegui
      Abstract: The field of artificial intelligence has significantly advanced over the past decades, inspired by discoveries from the fields of biology and neuroscience. The idea of this work is inspired by the process of self-organization of cortical areas in the human brain from both afferent and lateral/internal connections. In this work, we develop a brain-inspired neural model associating Self-Organizing Maps (SOM) and Hebbian learning in the Reentrant SOM (ReSOM) model. The framework is applied to multimodal classification problems. Compared to existing methods based on unsupervised learning with post-labeling, the model enhances the state-of-the-art results. This work also demonstrates the distributed and scalable nature of the model through both simulation results and hardware execution on a dedicated FPGA-based platform named SCALP (Self-configurable 3D Cellular Adaptive Platform). SCALP boards can be interconnected in a modular way to support the structure of the neural model. Such a unified software and hardware approach enables the processing to be scaled and allows information from several modalities to be merged dynamically. The deployment on hardware boards provides performance results of parallel execution on several devices, with the communication between each board through dedicated serial links. The proposed unified architecture, composed of the ReSOM model and the SCALP hardware platform, demonstrates a significant increase in accuracy thanks to multimodal association, and a good trade-off between latency and power consumption compared to a centralized GPU implementation.
      PubDate: 2022-03-02T00:00:00Z
       
  • The BrainScaleS-2 Accelerated Neuromorphic System With Hybrid Plasticity

    • Authors: Christian Pehle, Sebastian Billaudelle, Benjamin Cramer, Jakob Kaiser, Korbinian Schreiber, Yannik Stradmann, Johannes Weis, Aron Leibfried, Eric Müller, Johannes Schemmel
      Abstract: Since the beginning of information processing by electronic components, the nervous system has served as a metaphor for the organization of computational primitives. Brain-inspired computing today encompasses a class of approaches ranging from using novel nano-devices for computation to research into large-scale neuromorphic architectures, such as TrueNorth, SpiNNaker, BrainScaleS, Tianjic, and Loihi. While implementation details differ, spiking neural networks—sometimes referred to as the third generation of neural networks—are the common abstraction used to model computation with such systems. Here we describe the second generation of the BrainScaleS neuromorphic architecture, emphasizing applications enabled by this architecture. It combines a custom analog accelerator core supporting the accelerated physical emulation of bio-inspired spiking neural network primitives with a tightly coupled digital processor and a digital event-routing network.
      PubDate: 2022-02-24T00:00:00Z
       
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
 


Your IP address: 44.192.25.113
 
Home (Search)
API
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-