{"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":37,"pdf_page":45,"physical_index":45,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"8a97542fea1bbac65a55f5558c1c40b2c78b5602804f401b03720d94db6b374c"},"chapter":"人工智能哲学","content":"$$\nP r _ { 1 } ( z _ { 2 } , z _ { 3 } - z z _ { n } )\\tag{6}\n$$\n\n式中 $z z _ { n }$ 代表n，而 $z z _ { p }$ 代表 $2 ^ { p }$ 。经过重复替代，对代表s的任何数字$z z _ { 2 }$ 来说，我们就得到一个表达式：\n\n$$\n\\begin{array} { r l } & { ( z _ { 1 } ) z z _ { p } \\colon P r _ { 1 } ( z _ { 1 } , z z _ { n } z z _ { 2 } ) _ { \\bullet } \\equiv . ( E z _ { 2 } ) z z _ { p } ( E z _ { 3 } ) z z _ { p } \\cdots ( E z _ { n } ) z z _ { p } . } \\\\ & { P r _ { 2 } ( z _ { 1 } , z _ { 2 } , z z _ { n } ( z z _ { 2 } - 1 ) ) . P r _ { 2 } ( z _ { 2 } , z _ { 3 } , z z _ { n } ( z z _ { 2 } - 1 ) ) . \\cdots . } \\\\ & { P r _ { 2 } ( z _ { n - 1 } , z _ { n } , 0 ) . P r _ { 1 } ( z _ { n } , 0 ) _ { \\circ } } \\end{array}\\tag{7}\n$$\n\n通过归纳，不难证明它与下式等效：\n\n$$\n\\begin{array} { r l } & { ( z _ { 1 } ) z z _ { p } \\ldots P r _ { 1 } ( z _ { 1 } , z z _ { n } z z _ { 2 } ) \\div \\equiv \\colon \\ : ( E f ) ( z _ { 2 } ) z z _ { 2 } - 1 f ( z _ { 2 } z z _ { n } ) } \\\\ & { z z _ { p } . \\ : f ( z z _ { n } z z _ { 2 } ) = z _ { 1 } . \\ : P r _ { 2 } ( f ( z z _ { n } ( z _ { 2 } + 1 ) ) , } \\\\ & { f ( z z _ { n } z z _ { 2 } ) ) . \\ : P r _ { 1 } ( f ( 0 ) , \\ : 0 ) } \\end{array}\\tag{8}\n$$\n\n既然这对所有 $z z _ { 2 }$ 都适用，因此下式也成立：\n\n$$\n\\begin{array} { r l } & { ( z _ { 4 } ) ( z _ { 1 } ) z z _ { p } \\colon P r _ { 1 } ( z _ { 1 } , z _ { 4 } ) _ { \\star } \\equiv _ { \\star } ( E f ) ( z _ { 2 } ) ( z _ { 4 } - 1 ) _ { \\star } f ( z _ { 2 } ) } \\\\ & { \\leqslant z z _ { p } \\star f ( z _ { 4 } ) = z _ { 1 } f ( z _ { 4 } ) = z _ { 1 } \\cdot P r _ { 2 } \\ \\left[ f ( z _ { 2 } + 1 ) , f ( z _ { 2 } ) , z _ { 2 } \\right] \\ , } \\\\ & { P r _ { 1 } \\ \\left[ f ( r e s ( z _ { 4 } , z z _ { n } ) ) , r e s ( z _ { 4 } , z z _ { n } ) \\right] \\ , } \\end{array}\\tag{9}\n$$\n\n式中 $z z _ { n }$ 代表n， $r e s ( r , s )$ 是r除以s的余数，而 $z z _ { p }$ 代表 $2 ^ { p }$ 。它可以近似地写成\n\n$$\n\\begin{array} { r l } & { N _ { i } ( t ) . \\equiv . \\left( E \\varPhi \\right) ( x ) t { - } 1 . \\Phi ( x ) { \\leqslant } 2 ^ { p } . \\Phi ( t ) } \\\\ & { \\qquad = i . P \\left[ \\Phi ( x { + } 1 ) , \\Phi ( x ) . N \\varPhi ( _ { 0 } ) ( 0 ) \\right] , } \\end{array}\n$$\n\n假定式中 x和t也能被n除尽，而 $P r _ { 2 }$ 代表 $P _ { \\circ }$ 根据前面的论述，我们得到定理VI。\n\n定理VⅢI\n\n表达式(9)表示网H的那组循环神经元，它和用这组神经元表达其他神经元动作的某个TPE一起，构成了网H的一个解答。\n\n现在来考虑一组 $S _ { i }$ 的可实现性问题。由简单归纳可证得的第一个必要条件是，如果对 $S _ { i }$ 中其他自由变量p存在着类似陈述，即任何神经网都不能计及未来的周围传入神经，则下式成立：\n\n1 神经活动内在概念的逻辑演算\n\n37","previous_page":36,"next_page":38}