Article
Computer Science, Artificial Intelligence
Yun Zhang, Hong Qu, Xiaoling Luo, Yi Chen, Yuchen Wang, Malu Zhang, Zefang Li
Summary: In this paper, a Recursive Least Squares-Based Learning Rule (RLSBLR) for Spiking Neural Networks (SNNs) is proposed to generate desired spatio-temporal spike trains. Experimental results in different settings show that the proposed RLSBLR outperforms competitive algorithms in terms of learning accuracy, efficiency, and robustness against noise. The integration of modified synaptic delay learning further improves the learning performance.
Article
Computer Science, Artificial Intelligence
Jianxiong Tang, Jian-Huang Lai, Xiaohua Xie, Lingxiao Yang, Wei-Shi Zheng
Summary: This paper proposes a fast and memory-efficient Activation Consistency Coupled ANN-SNN (AC2AS) framework for training SNN in low-power environments. The framework utilizes a weight-shared architecture between ANN and SNN, as well as spiking mapping units, to achieve fast training and ensure activation consistency for SNN. Experimental results show that AC2AS-based models perform well on benchmark datasets and achieve comparable accuracy with reduced time steps, training time, GPU memory costs, and spike activities compared to the Spike-based BP model.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Gexiang Zhang, Xihai Zhang, Haina Rong, Prithwineel Paul, Ming Zhu, Ferrante Neri, Yew-Soon Ong
Summary: This paper introduces the application of biological neural systems and artificial neural networks in classification tasks, and proposes a novel type of spiking neural P system (LSN P system) to address classification problems. The LSN P system has a flexible structure and high classification performance, designed by mimicking the structure and behavior of biological cells. Experimental results demonstrate the feasibility and effectiveness of the proposed system, showing promising performance in solving real-world classification problems.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2022)
Article
Optics
Yanan Han, Shuiying Xiang, Zhenxing Ren, Chentao Fu, Aijun Wen, Yue Hao
Summary: A modified supervised learning algorithm for optical spiking neural networks is proposed in this study, which introduces synaptic time-delay plasticity to improve performance. The proposed algorithm outperforms traditional weight-based methods in tasks of spike sequence learning and classification.
PHOTONICS RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Nitin Rathi, Kaushik Roy
Summary: This article proposes a low-latency deep spiking network called DIET-SNN, which optimizes the membrane leak and firing threshold to reduce latency while maintaining competitive accuracy. Through evaluation and comparative experiments, DIET-SNN shows excellent performance in image classification tasks with efficient computational capabilities.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Qiang Yu, Shiming Song, Chenxiang Ma, Jianguo Wei, Shengyong Chen, Kay Chen Tan
Summary: This article focuses on developing temporal-based SNN methods to enhance the accuracy of image recognition while maintaining efficiency. The research shows that under various conditions, these methods exhibit efficient and effective performance, even comparable to rate-based ones, but with a lighter network structure and fewer spikes.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Tiandou Hu, Xianghong Lin, Xiangwen Wang, Pangao Du
Summary: This paper proposes a spike optimization mechanism to enhance the performance and efficiency of supervised learning algorithms in multilayer SNNs. By selecting optimal presynaptic spikes for computing the change amount of synaptic weights, the mechanism considers the correlation between desired and actual output spikes of the network. The application of the mechanism improves learning performance and reduces the running time of the algorithms.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Sergio F. Chevtchenko, Teresa B. Ludermir
Summary: This study combines a pre-trained binary convolutional neural network with an SNN trained online through reward-modulated STDP to leverage the advantages of both models. Experimental results show that this architecture can be a competitive alternative to deep reinforcement learning in high-dimensional observation environments.
Article
Engineering, Biomedical
S. J. Pawan, Govind Jeevan, Jeny Rajan
Summary: In this paper, a mixup-based risk minimization operator in a student-teacher-based semi-supervised paradigm is proposed, along with structure-aware constraints, to enforce consistency among the student and teacher predictions. The method shows computational advantages and performs well in medical image segmentation.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Yijun Song, Jingwen Wang, Lin Ma, Jun Yu, Jinxiu Liang, Liu Yuan, Zhou Yu
Summary: In this paper, we propose a novel weakly-supervised model called Multi-level Attentional Reconstruction Networks (MARN) for video temporal grounding. MARN leverages attentional reconstruction to train an attention map that can reconstruct the given query, and ranks proposals based on attention scores to localize the most suitable segment. It effectively aligns video-level supervision and proposal scoring, and incorporates a multi-level framework to generate and score variable-length and fix-length time sequences.
Article
Neurosciences
Guanlin Wu, Dongchen Liang, Shaotong Luan, Ji Wang
Summary: In recent years, there has been a growing demand for using spiking neural networks (SNNs) to implement artificial intelligent systems. A new temporal coding method has been proposed to train SNNs while preserving their asynchronous nature. This method, combined with self-incremental variables and an encoding method, enables SNNs to achieve comparable performance in reinforcement learning tasks as state-of-the-art artificial neural networks.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Computer Science, Information Systems
Rui Miao, Yintao Yang, Yao Ma, Xin Juan, Haotian Xue, Jiliang Tang, Ying Wang, Xin Wang
Summary: Graph neural networks (GNNs) have been successful in handling graph structured data. Due to limited labeled data, contrastive learning is applied to the graph domain. Existing node-level graph contrastive learning methods face challenges of high computational cost and inaccurate negative sample selection. To address these challenges, we propose a strategy for sampling a subset of nodes and utilize classification prediction to guide the selection of negative samples. Our approach, named GCNSS, achieves faster training and improves the performance of existing GNN models in semi-supervised node classification tasks.
INFORMATION SCIENCES
(2022)
Article
Telecommunications
Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
Summary: This paper introduces the operation principle, training algorithms, and models of Spiking Neural Networks (SNNs) and compares two main methods. To address the non-differentiability of the spiking mechanism, a differentiable function approximating the threshold activation function is proposed, and an alternative method based on probability models is discussed. Finally, experimental results on accuracy and convergence under different SNN models are provided.
IEEE COMMUNICATIONS LETTERS
(2021)
Article
Automation & Control Systems
Junxiu Liu, Hao Lu, Yuling Luo, Su Yang
Summary: Spiking Neural Networks (SNNs) mimic the time encoding and information processing aspects of the human brain. A multi-task autonomous learning paradigm is proposed for mobile robot applications using SNNs, with a focus on developing a Reward-modulated Spiking-time-dependent Plasticity learning rule.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Mathematics, Applied
Iftikhar Ahmad, Hira Ilyas, Muhammad Asif Zahoor Raja, Tahir Nawaz Cheema, Hasnain Sajid, Kottakkaran Sooppy Nisar, Muhammad Shoaib, Mohammed S. Alqahtani, C. Ahamed Saleel, Mohamed Abbas
Summary: This article investigates the effects of recurring malaria re-infection on the spread dynamics of the disease using a supervised learning based neural networks model. The study aims to discuss the dynamics of malaria spread and improve prediction and analysis through the use of Levenberg-Marquardt artificial neural networks (LMANNs) and numerical treatment of the malaria model. The results show the reliable performance and efficacy of the LMANNs model.