We study the learning problem associated with spiking neural networks. Specifically, we focus on spiking neural networks composed of simple spiking neurons having only positive synaptic weights, equipped with an affine encoder and decoder; we refer to these as affine spiking neural networks. These neural networks are shown to depend continuously on their parameters, which facilitates classical covering number-based generalization statements and supports stable gradient-based training. We demonstrate that the positivity of the weights enables a wide range of expressivity results, including rate-optimal approximation of smooth functions and dimension-independent approximation of Barron regular functions. In particular, we show in theory and simulations that affine spiking neural networks are capable of approximating shallow ReLU neural networks. Furthermore, we apply these affine spiking neural networks to standard machine learning benchmarks and reach competitive results. Finally, we observe that from a generalization perspective, contrary to feedforward neural networks or previous results for general spiking neural networks, the depth has little to no adverse effect on the generalization capabilities.
Spike Agreement Dependent Plasticity: A scalable Bio-Inspired learning paradigm for Spiking Neural Networks
School of Data Science, Indian Institute of Science Education and Research, Thiruvananthapuram, India（数据科学学院，印度科学教育与研究学院，特里布文纳纳特帕尔姆，印度）；School of Data Science, Indian Institute of Science Education（数据科学学院，印度科学教育与研究学院）；School of Physics, Indian Institute of Science Education（物理学院，印度科学教育与研究学院）
Efficiently Training Time-to-First-Spike Spiking Neural Networks from Scratch
Shenzhen Graduate School, Peking University（北京大学深圳研究生院）；Pengcheng Laboratory（鹏城实验室）；School of Computer Science, Peking University（北京大学计算机学院）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Centre de Recherche Cerveau et Cognition (CERCO), UMR5549 CNRS - Univ. Toulouse 3（法国国家科学研究中心-图卢兹第三大学大脑与认知研究中心）
Decoding finger velocity from cortical spike trains with recurrent spiking neural networks
Qiushi Academy for Advanced Studies, Zhejiang University（浙江大学求是高等研究院）；College of Biomedical Engineering and Instrument Science, Zhejiang University（浙江大学生物医学工程与仪器科学学院）；Friedrich Miescher Institute for Biomedical Research（弗里德里希·米歇尔生物医学研究所）；Faculty of Science, University of Basel（巴塞尔大学理学院）；China Nanhu Academy of Electronics and Information Technology (CNAEIT)（中国南湖电子信息技术研究院）
Enabling Energy-Efficient Simultaneous Multi-Task Reinforcement Learning through Spiking Neural Networks with Active Dendrites for Bio-inspired Generalist Agents
eBRAIN Lab New York University (NYU) Abu Dhabi（eBRAIN实验室 新 York大学（NYU）阿布扎赫德）
Spiking Neural Networks for fMRI-Based Visual Semantic Decoding
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；State Key Laboratory of Media Convergence and Communication, Communication University of China（中国传媒大学媒体融合与传播国家重点实验室）
