{"id":239,"date":"2023-12-31T19:01:42","date_gmt":"2023-12-31T19:01:42","guid":{"rendered":"https:\/\/alandix.com\/aibook\/?page_id=239"},"modified":"2023-12-31T19:01:42","modified_gmt":"2023-12-31T19:01:42","slug":"chap06","status":"publish","type":"page","link":"https:\/\/alandix.com\/aibook\/second-edition\/toc2e\/chap06\/","title":{"rendered":"Chapter 6 \u2013 Neural Networks"},"content":{"rendered":"<div class=\"embedurl\" data-url=\"https:\/\/alandix.com\/books\/aibook\/content\/chaps\/chap06.html\" ><!--  Chapter 6 Neural Networks  -->\n\n<script>\nvar chapnos = 6;\nvar json_url = \"https:\\\/\\\/alandix.com\\\/books\\\/aibook\\\/content\\\/chaps\\\/chap06.json\";\n<\/script>\n\n\n\n\n\t<object style=\"width:100%; aspect-ratio: 10 \/ 7;\" type=\"application\/pdf\" data=\"https:\/\/alandix.com\/books\/aibook\/content\/slides-pdf\/AI-chap-06.pdf\"><\/object>\n\t<p> Download <a href=\"https:\/\/alandix.com\/books\/aibook\/content\/slides-pptx\/AI-chap-06.pptx\" download>chapter slides<\/a><\/p>\n\n\n<h3> Contents <\/h3>\n<div class=\"toc\">\n<dl>\n<dt>6.1&nbsp;&nbsp;Overview<\/dt>\n<dt>6.2&nbsp;&nbsp;Why Use Neural Networks?<\/dt>\n<dt>6.3&nbsp;&nbsp;The Perceptron<\/dt><dd><dl>\n<dt>6.3.1&nbsp;&nbsp;The XOR Problem<\/dt>\n<\/dl><\/dd>\n<dt>6.4&nbsp;&nbsp;The Multi-layer Perceptron<\/dt>\n<dt>6.5&nbsp;&nbsp;Backpropagation<\/dt><dd><dl>\n<dt>6.5.1&nbsp;&nbsp;Basic Principle<\/dt>\n<dt>6.5.2&nbsp;&nbsp;Backprop for a Single Layer Network<\/dt>\n<dt>6.5.3&nbsp;&nbsp;Backprop for hidden layers<\/dt>\n<\/dl><\/dd>\n<dt>6.6&nbsp;&nbsp;Associative Memories<\/dt><dd><dl>\n<dt>6.6.1&nbsp;&nbsp;Boltzmann Machines<\/dt>\n<dt>6.6.2&nbsp;&nbsp;Kohonen Self-organising Networks<\/dt>\n<\/dl><\/dd>\n<dt>6.7&nbsp;&nbsp;Lower-level Models<\/dt><dd><dl>\n<dt>6.7.1&nbsp;&nbsp;Cortical Layers<\/dt>\n<dt>6.7.2&nbsp;&nbsp;Inhibition<\/dt>\n<dt>6.7.3&nbsp;&nbsp;Spiking Neural Networks<\/dt>\n<\/dl><\/dd>\n<dt>6.8&nbsp;&nbsp;Hybrid Architectures<\/dt><dd><dl>\n<dt>6.8.1&nbsp;&nbsp;Hybrid Layers<\/dt>\n<dt>6.8.2&nbsp;&nbsp;Neurosymbolic AI<\/dt>\n<\/dl><\/dd>\n<dt>6.9&nbsp;&nbsp;Summary<\/dt>\n<\/dl><\/div>\n\n\n<h3> Glossary items referenced in this chapter <\/h3>\n<div class=\"toc\">\n<a href=\"https:\/\/alandix.com\/glossary\/aibook\/alphago\">AlphaGo<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/analogy\">analogy<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/artificial%20neural%20networks\">artificial neural networks<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/associative%20memory\">associative memory<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/auto-associative%20memory\">auto-associative memory<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/autoencoder\">autoencoder<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/backpropagation\">backpropagation<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/big%20data\">big data<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/boltzmann%20machine\">Boltzmann machine<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/brain%20architecture\">brain architecture<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/cerebral%20cortex\">cerebral cortex<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/classification\">classification<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/clustering\">clustering<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/cognitive%20architecture\">cognitive architecture<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/computer%20chess\">computer chess<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/connectionist%20model\">connectionist model<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/converge\">converge<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/counterfactual%20reasoning\">counterfactual reasoning<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/data%20reduction\">data reduction<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/decision%20tree\">decision tree<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/deep%20fakes\">deep fakes<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/deep%20neural%20network\">deep neural network<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/delta\">delta<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/differential%20%28calculus%29\">differential (calculus)<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/disambiguation\">disambiguation<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/emotion\">emotion<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/event\">event<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/expert%20system\">expert system<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/fault%20tolerant\">fault tolerant<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/fmri\">fMRI<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/fourier%20analysis\">Fourier analysis<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/frequency%20domain\">frequency domain<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/fully%20connected\">fully connected<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/game%20playing\">game playing<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/genetic%20programming\">genetic programming<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/gestalt\">gestalt<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/gpt-3\">GPT-3<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/graceful%20degradation\">graceful degradation<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/grey%20matter\">grey matter<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/heteroassociative%20memory\">heteroassociative memory<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/heuristic%20evaluation%20function\">heuristic evaluation function<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/hill%20climbing%20algorithm\">hill climbing algorithm<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/human%20brain%20project\">Human Brain Project<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/human%20intelligence\">human intelligence<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/human%20labelling\">human labelling<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/human%20memory\">human memory<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/human%20perception\">human perception<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/hybrid\">hybrid<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/hybrid%20ai\">hybrid AI<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/hybrid%20architecture\">hybrid architecture<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/hybrid%20layers\">hybrid layers<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/inhibition\">inhibition<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/knowledge%20base\">knowledge base<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/kohonen%20network\">Kohonen networks<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/lateral%20inhibition\">lateral inhibition<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/linear%20discriminant%20analysis\">linear discriminant analysis<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/linearly%20inseparable\">linearly inseparable<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/linearly%20separable\">linearly separable<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/logistic%20function\">logistic function<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/machine%20learning\">machine learning<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/memory\">memory<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/monte%20carlo%20search\">Monte Carlo search<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/multi-layer%20neural%20network\">multi-layer neural network<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/multi-layer%20perceptron\">multi-layer perceptron<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/mutual%20inhibition\">mutual inhibition<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/nettalk\">NETtalk <\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/neural-network%20architecture\">neural-network architecture<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/neuron\">neuron<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/neurone\">neurone<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/neurosymbolic%20ai\">neurosymbolic AI<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/object%20recognition\">object recognition<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/openai\">OpenAI<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/parallel%20processing\">parallel processing<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/pattern%20recognition\">pattern recognition<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/pavlovian%20learning\">Pavlovian learning<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/perceptron\">perceptron<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/phoneme%20labelling\">phoneme labelling<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/phonetic%20typewriter\">phonetic typewriter<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/regret\">regret<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/reinforcement%20learning\">reinforcement learning<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/relaxation%20term\">relaxation term<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/rescue%20dogs\">rescue dogs<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/reservoir%20computing\">reservoir computing<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/restricted%20boltzmann%20machine\">restricted Boltzmann machine<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/search\">search<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/self-organising%20map\">self-organising map<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/semantic%20network\">semantic network<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/sigmoid%20activation%20function\">sigmoid activation function<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/sigmoid%20function\">sigmoid function<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/similarity%20matrix\">similarity matrix<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/sleeping%20phase\">sleeping phase<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/sparsely%20connected\">sparsely connected<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/speech%20recognition\">speech recognition<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/spikes\">spikes<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/spiking%20neural%20network\">spiking neural network<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/spin%20glass%20models\">spin glass models<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/sub-symbolic%20systems\">sub-symbolic systems<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/supervised%20learning\">supervised learning<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/support%20vector%20machine\">support vector machine<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/symbolic%20systems\">symbolic systems<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/threshold\">threshold<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/threshold%20function\">threshold function<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/training%20phase\">training phase<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/trigger\">trigger<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/underdetermined\">underdetermined<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/unsupervised%20learning\">unsupervised learning<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/upper%20bound\">upper bound<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/white%20matter\">white matter<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/xor%20problem\">XOR problem<\/a><\/strong><\/div>\n\n\n\n\n<\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":2,"featured_media":0,"parent":221,"menu_order":6,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_themeisle_gutenberg_block_has_review":false,"footnotes":""},"class_list":["post-239","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/pages\/239","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/comments?post=239"}],"version-history":[{"count":3,"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/pages\/239\/revisions"}],"predecessor-version":[{"id":296,"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/pages\/239\/revisions\/296"}],"up":[{"embeddable":true,"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/pages\/221"}],"wp:attachment":[{"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/media?parent=239"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}