{"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":36,"pdf_page":44,"physical_index":44,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"caa6310fec1dfe888de58256b2e338c2e03a328ae17087c657f4eb6b19aa71a9"},"chapter":"人工智能哲学","content":"$$\n{ \\cal N } _ { i } ( z _ { 1 } ) . \\equiv . P r _ { i } \\left[ S ^ { n _ { * } } N _ { 1 } ( z _ { 1 } ) , S ^ { n _ { * } } N _ { 2 } ( z _ { 1 } ) , \\cdots , S ^ { n _ { * } } N _ { p } ( z _ { 1 } ) \\right]\\tag{2}\n$$\n\n式中 $P r _ { i }$ 也涉及周围传入神经。如果n是 $n _ { i j }$ 的最小公倍数，那么按照(2)式，以周围传入神经的等价物替换 $N _ { j }$ ，并且在所得结果上将这个过程重复足够多的次数，我们就获得如下形式的S：\n\n$$\n{ \\cal N } _ { i } ( z _ { 1 } ) . \\equiv . P r _ { 1 } \\left[ S ^ { n } { \\cal N } _ { 1 } ( z _ { 1 } ) , S ^ { n } { \\cal N } _ { 2 } ( z _ { 1 } ) , \\cdots , S ^ { n } { \\cal N } _ { p } ( z _ { 1 } ) \\right] \\ _ { \\mathrm { ~ o ~ } }\\tag{3}\n$$\n\n这些表达式可以用希尔伯特析取的正则形式写成：\n\n$$\nN _ { i } ( z _ { 1 } ) . \\equiv . \\sum _ { \\stackrel { \\alpha \\neq k } { \\beta \\atop \\beta \\alpha } } S _ { a } \\prod _ { j \\underset { k } { \\varepsilon \\pm k } } S ^ { n } N _ { j } ( z _ { 1 } ) \\prod _ { j \\underset { k } { \\varepsilon \\pm k } } \\sim S ^ { n } N _ { j } ( z _ { 1 } ) ,\n$$\n\n对适当的k，\n\n(4)\n\n式中 $S _ { a }$ 是一个网H的绝对传入神经的TPE。这里大约有 $2 ^ { p }$ 个不同的语句，由 $p N _ { i }$ 构成，采用方法是把它们之中某一部分的合取与其余部分的否定的合取结合起来。若由 $X _ { 1 } ( z _ { 1 } ) , X _ { 2 } ( z _ { 1 } ) , \\cdots , X _ { 2 p } ( z _ { 1 } )$ 对其数值化，我们可以通过使用表达式(4)得出如下形式的一组等效方程：\n\n$$\nX _ { i } ( z _ { 1 } ) . \\equiv . \\sum _ { j = 1 } ^ { 2 p } P r _ { i j } ( z _ { 1 } ) . S ^ { n } X _ { j } ( z _ { 1 } ) _ { \\circ }\\tag{5}\n$$\n\n现在我们把下标数i，j引入对象语言，即定义 $P r _ { 1 }$ 和 $P r _ { 2 }$ ，使得每当$z z _ { 1 }$ 和 $z z _ { 2 }$ 分别代表i和j时，就可证明 $P r _ { 1 } ( z z _ { 1 } , \\ z _ { 1 } ) . \\equiv . X _ { i } ( z _ { 1 } )$ 和 $P r _ { 2 }$ $( z z _ { 1 } , \\ z z _ { 2 } , \\ z _ { 1 } ) . \\equiv . P r _ { i j } ( z _ { 1 } )$\n\n这样我们可以把(5)式重写成：\n\n$$\n( z _ { 1 } ) z z _ { p } : P r _ { 1 } ( z _ { 1 } , z _ { 3 } ) . \\equiv . ( E z _ { 2 } ) z z _ { p } . P r _ { 2 } ( z _ { 1 } , z _ { 2 } , z _ { 3 } - z z _ { n } ) .\n$$\n\n人工智能哲学\n\n36","previous_page":35,"next_page":37}