{"resolved":true,"match_type":"uuid","source_type":"original_book","book_id":"7f418071-0fdc-4a5a-a4c5-82dd1979d9c2","title":"人工智能哲学","author":null,"edition":null,"publisher":null,"year":null,"isbn":"7532740544","requested_by":"printed_page","book":{"source_type":"original_book","book_id":"7f418071-0fdc-4a5a-a4c5-82dd1979d9c2","id":"7f418071-0fdc-4a5a-a4c5-82dd1979d9c2","uuid":"7f418071-0fdc-4a5a-a4c5-82dd1979d9c2","title":"人工智能哲学","normalized_title":"人工智能哲学","author":null,"edition":null,"publisher":null,"year":null,"isbn":"7532740544","isbns":["7532740544"],"parsed":true,"ai_readable":true,"document_type":"book","page_count":501,"navigation_url":"https://workshop.closeclaw.top/ai/book/7f418071-0fdc-4a5a-a4c5-82dd1979d9c2","title_url":"https://workshop.closeclaw.top/ai/title/%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD%E5%93%B2%E5%AD%A6","fixed_page_url_template":"https://workshop.closeclaw.top/ai/book/7f418071-0fdc-4a5a-a4c5-82dd1979d9c2/page/{printed_page}","path_api_url_template":"https://workshop.closeclaw.top/api/ai/book/7f418071-0fdc-4a5a-a4c5-82dd1979d9c2/page/{printed_page}","read_url":"https://workshop.closeclaw.top/api/ai/read/7f418071-0fdc-4a5a-a4c5-82dd1979d9c2","page_url":"https://workshop.closeclaw.top/api/ai/books/7f418071-0fdc-4a5a-a4c5-82dd1979d9c2/page","search_url":"https://workshop.closeclaw.top/api/ai/books/7f418071-0fdc-4a5a-a4c5-82dd1979d9c2/search"},"page":{"printed_page":380,"pdf_page":388,"physical_index":388,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"1a37ba86417ffe56a924f2f8c77791a5051eebd2399d8526827bcf24348ee802"},"chapter":"人工智能哲学","content":"$$\n\\{ \\mathbf { a } , \\ \\mathbf { b } , \\ \\mathbf { c } , \\ \\mathbf { d } \\} \\ . \\left[ \\begin{array} { l l l } { \\mathbf { p } _ { 1 } } & { \\mathbf { q } _ { 1 } } & { \\mathbf { f } _ { 1 } } \\\\ { \\mathbf { p } _ { 2 } } & { \\mathbf { q } _ { 2 } } & { \\mathbf { f } _ { 2 } } \\\\ { \\mathbf { p } _ { 3 } } & { \\mathbf { q } _ { 3 } } & { \\mathbf { f } _ { 3 } } \\\\ { \\mathbf { p } _ { 4 } } & { \\mathbf { q } _ { 4 } } & { \\mathbf { r } _ { 4 } } \\end{array} \\right] = \\ \\{ \\mathbf { x } , \\ \\mathbf { y } , \\ \\mathbf { z } \\}\n$$\n\n这种代数运算可以通过图14-9的神经分布，用物理方式相当简单地予以实现。右边的平行传入纤维分别把一串电化学“脉冲”送往那些等候着的树突树。数字a，b，c，d表示四根纤维各自的瞬间脉冲频率高于(正数)或低于(负数)某一基准脉冲频率的量。例如，最上面的传入纤维分别与三个传出细胞形成突触，各产生一个刺激联系，使细胞胞体去极化，并把一个脉冲沿着它的纵向传出轴突向下送出。每一个细胞的脉冲发射的输出频率取决于：(1)它从所有传入的突触联系接收到的输人刺激的单个频率。(2)每个突触联系的加权值或强度，由突触的布局和它们的截面积确定。这些强度值分别由图14-8中矩阵的系数来表示。于是，神经的相互联结特性实现了这个矩阵。图14-9中的三个细胞分别把它们接收到的刺激“加”起来，并沿着传出轴突向下发出一串适当的脉冲。这三个输出频率不同于三个传出细胞的背景频率或基准频率，相差量或正或负，这些量对应于输出矢量{x，y，z}。\n\n注意，对于状态空间分层结构来说，信息编码是一个神经事件的空间定位的问题。与此不同，对所讨论的矩阵乘法的计算类型来说，输入和输出变量是由相关通路中的几组脉冲频率来编码的。前一系统使用“空间编码”，后一系统使用“频率编码”。但两种系统所从事的都是状态空间位置的坐标变换。\n\n人工智能哲学\n\n380","previous_page":379,"next_page":381}