{"resolved":true,"match_type":"uuid","source_type":"original_book","book_id":"07d591c2-0f4c-45ac-a1d7-103c4807db8f","title":"数字经济：内涵与路径","author":null,"edition":null,"publisher":null,"year":null,"isbn":"9787521745023","requested_by":"printed_page","book":{"source_type":"original_book","book_id":"07d591c2-0f4c-45ac-a1d7-103c4807db8f","id":"07d591c2-0f4c-45ac-a1d7-103c4807db8f","uuid":"07d591c2-0f4c-45ac-a1d7-103c4807db8f","title":"数字经济：内涵与路径","normalized_title":"数字经济内涵与路径","author":null,"edition":null,"publisher":null,"year":null,"isbn":"9787521745023","isbns":["9787521745023"],"parsed":true,"ai_readable":true,"document_type":"book","page_count":361,"navigation_url":"https://workshop.closeclaw.top/ai/book/07d591c2-0f4c-45ac-a1d7-103c4807db8f","title_url":"https://workshop.closeclaw.top/ai/title/%E6%95%B0%E5%AD%97%E7%BB%8F%E6%B5%8E%EF%BC%9A%E5%86%85%E6%B6%B5%E4%B8%8E%E8%B7%AF%E5%BE%84","fixed_page_url_template":"https://workshop.closeclaw.top/ai/book/07d591c2-0f4c-45ac-a1d7-103c4807db8f/page/{printed_page}","path_api_url_template":"https://workshop.closeclaw.top/api/ai/book/07d591c2-0f4c-45ac-a1d7-103c4807db8f/page/{printed_page}","read_url":"https://workshop.closeclaw.top/api/ai/read/07d591c2-0f4c-45ac-a1d7-103c4807db8f","page_url":"https://workshop.closeclaw.top/api/ai/books/07d591c2-0f4c-45ac-a1d7-103c4807db8f/page","search_url":"https://workshop.closeclaw.top/api/ai/books/07d591c2-0f4c-45ac-a1d7-103c4807db8f/search"},"page":{"printed_page":100,"pdf_page":99,"physical_index":99,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"f4c97168fe8c3962c93623a45dc6c07608196bc499c7d9e90569fac2af57b505"},"chapter":"第三章","content":"③类脑学习与处理算法（软件）\n\n神经形态模型是神经形态计算的重要组成部分，是在现有计算机硬件系统上实施对生物脑神经网络的模拟。\n\n神经形态模型的基本组成单元是神经元模型，即模仿树突、轴突和突触结构的模型。脑神经元之间的通信依靠神经细胞膜电位的升降脉冲，借鉴该原理，研究人员提出了多种神经元模型，例如Integrate-and-Fire（I&F）模型、Leak Integrate-and-Fire（LIF）模型等。神经元模型越接近真实神经元的结构特性，其模型就越复杂，模型应用效果在原则上也会越好。\n\n神经网络模型描述神经元突触的连接关系，一方面可以遵从生物原理，另一方面可与生物网络具有不同的拓扑结构。应用神经网络模型，不同的神经元和突触模型可组成多种多样的神经网络，从而形成种类丰富的神经形态模型。<sup>31</sup> 脉冲神经网络（Spiking Neural Networks，SNN）作为第三代神经网络，相较于目前应用效果较好的卷积神经网络（Convolutional Neural Network，CNN）和循环神经网络（RecurrentNeural Network，RNN）等第二代神经网络，更加贴近脑神经元信息传递方式。<sup>30</sup> 尽管SNN在结构上对硬件实现更友好，但训练存在一定难度，当前很多团队正致力于开发SNN监督式学习规则，但SNN的实际应用依然较少。\n\n100","previous_page":99,"next_page":101}