{"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":33,"pdf_page":41,"physical_index":41,"physical_index_base":0,"printed_page_status":"recognized","page_sha256":"7ea394f74b1237d079152197b1c0c6c026126a019cd67381d5c8c9a0e7dbfceb"},"chapter":"人工智能哲学","content":"$$\n\\begin{array} { r l } & { N _ { 3 } ( t ) : \\equiv : N _ { ! } ( t - 1 ) . \\vee . N _ { ! } ( t - 3 ) . \\sim N _ { ! } ( t - 2 ) } \\\\ & { N _ { 4 } ( t ) . \\equiv . N _ { 2 } ( t - 2 ) . N _ { ! } ( t - 1 ) } \\end{array}\n$$\n\n为简单起见，这里我们假定冷的感觉需要持续大约两个突触延迟，相比之下热的感觉只需一个延迟。这些条件显然低于定理Ⅲ。因此可用定理Ⅱ的方法构造出一个网来实现它们。开始时，我们用图1-1a，b，c，d中实现的运算，把它们写成能显示出它们组成成分的形式，即这种形式：\n\n$$\n\\begin{array} { r l } & { N _ { 3 } ( t ) . \\equiv . S \\{ N _ { 1 } ( t ) \\vee S [ ( S N _ { 2 } ( t ) ) . \\sim N _ { 2 } ( t ) ] \\} } \\\\ & { N _ { 4 } ( t ) . \\equiv . S \\{  [ S N _ { 2 } ( t ) ]  . N _ { 2 } ( t ) \\} \\ \\mathrm { , } } \\end{array}\n$$\n\n我们首先为括在最里面的函数构造一个网，然后向外发展；在这种情况下，我们运行一个由图1-1a中所示那种形式的网，比如说，从神经元$c _ { 2 }$ 到某个神经元 $c _ { a }$ ，得到结果：\n\n$$\n\\smash { N _ { a } ( t ) _ { 3 } \\equiv . S N _ { 2 } ( t ) _ { 3 } }\n$$\n\n下一步引人图1-1c和图1-1d形式的两个网，两者都从 $c _ { a }$ 和 $c _ { 2 }$ 开始运行，分别在 $c _ { 4 }$ 和比如说 $c _ { b }$ 结束。于是\n\n$$\n\\begin{array} { r l } & { N _ { 4 } ( t ) _ { \\cdot } \\equiv . S \\left[ N _ { a } ( t ) . N _ { 2 } ( t ) \\right] \\ , \\equiv . S \\left[ \\left( S N _ { 2 } ( t ) \\right) . N _ { 2 } ( t ) \\right] \\ , } \\\\ & { N _ { b } ( t ) _ { \\cdot } \\equiv . S \\left[ N _ { a } ( t ) . \\sim N _ { 2 } ( t ) \\right] \\ . } \\\\ & { \\equiv . S \\left[ \\left( S N _ { 2 } ( t ) \\right) . \\sim N _ { 2 } ( t ) \\right] \\ , } \\end{array}\n$$\n\n最后运行图1-1b形式的网，从 $c _ { 1 }$ 和 $c _ { b }$ 到 $c _ { 3 }$ ，并导出\n\n$$\n\\begin{array} { l } { { N _ { 3 } ( t ) . \\equiv . S \\left[ N _ { 1 } ( t ) \\vee N _ { b } ( t ) \\right] ~ . } } \\\\ { { \\ } } \\\\ { { \\equiv . S \\left\\{ N _ { 1 } ( t ) \\vee S \\left[ ( S N _ { 2 } ( t ) ) . \\sim N _ { 2 } ( t ) \\right] ~ \\right\\} ~ . } } \\end{array}\n$$\n\n$N _ { 3 } ( \\mathbf { \\varepsilon } _ { t } )$ 和 $N _ { 4 } ( \\mathfrak { t } )$ 的这些表达式就是所要求的表达式；而这一起实现作用的网在图1e 中完整地示出。\n\n这种幻觉使得感知和“外部世界”之间的对应关系依赖于中介神经网特殊结构特性这一事实非常清楚。当然，对应于不同的网，采用其他各种有关皮肤感受器行为的假定，也能产生同样的幻觉。\n\n1 神经活动内在概念的逻辑演算\n\n33","previous_page":32,"next_page":34}