{"id":243,"date":"2023-12-31T19:02:45","date_gmt":"2023-12-31T19:02:45","guid":{"rendered":"https:\/\/alandix.com\/aibook\/?page_id=243"},"modified":"2023-12-31T19:02:45","modified_gmt":"2023-12-31T19:02:45","slug":"chap08","status":"publish","type":"page","link":"https:\/\/alandix.com\/aibook\/second-edition\/toc2e\/chap08\/","title":{"rendered":"Chapter 8 \u2013 Going Large: deep learning and big data"},"content":{"rendered":"<div class=\"embedurl\" data-url=\"https:\/\/alandix.com\/books\/aibook\/content\/chaps\/chap08.html\" ><!--  Chapter 8 Going Large: Deep Learning and Big Data  -->\n\n<script>\nvar chapnos = 8;\nvar json_url = \"https:\\\/\\\/alandix.com\\\/books\\\/aibook\\\/content\\\/chaps\\\/chap08.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-08.pdf\"><\/object>\n\t<p> Download <a href=\"https:\/\/alandix.com\/books\/aibook\/content\/slides-pptx\/AI-chap-08.pptx\" download>chapter slides<\/a><\/p>\n\n\n<h3> Contents <\/h3>\n<div class=\"toc\">\n<dl>\n<dt>8.1&nbsp;&nbsp;Overview<\/dt>\n<dt>8.2&nbsp;&nbsp;Deep Learning<\/dt><dd><dl>\n<dt>8.2.1&nbsp;&nbsp;Why Are Many Layers so Difficult?<\/dt>\n<dt>8.2.2&nbsp;&nbsp;Architecture of the Layers<\/dt>\n<\/dl><\/dd>\n<dt>8.3&nbsp;&nbsp;Growing the Data<\/dt><dd><dl>\n<dt>8.3.1&nbsp;&nbsp;Modifying Real Data<\/dt>\n<dt>8.3.2&nbsp;&nbsp;Virtual Worlds<\/dt>\n<dt>8.3.3&nbsp;&nbsp;Self-Learning<\/dt>\n<\/dl><\/dd>\n<dt>8.4&nbsp;&nbsp;Data Reduction<\/dt><dd><dl>\n<dt>8.4.1&nbsp;&nbsp;Dimension Reduction<\/dt><dd><dl>\n<dt>8.4.1.1&nbsp;&nbsp;Vector Space Techniques<\/dt>\n<dt>8.4.1.2&nbsp;&nbsp;Non-numeric Features<\/dt>\n<\/dl><\/dd>\n<dt>8.4.2&nbsp;&nbsp;Reduce Total Number of Data Items<\/dt><dd><dl>\n<dt>8.4.2.1&nbsp;&nbsp;Sampling<\/dt>\n<dt>8.4.2.2&nbsp;&nbsp;Aggregation<\/dt>\n<\/dl><\/dd>\n<dt>8.4.3&nbsp;&nbsp;Segmentation<\/dt><dd><dl>\n<dt>8.4.3.1&nbsp;&nbsp;Class Segmentation<\/dt>\n<dt>8.4.3.2&nbsp;&nbsp;Result Recombination<\/dt>\n<dt>8.4.3.3&nbsp;&nbsp;Weakly Communicating Partial Analysis<\/dt>\n<\/dl><\/dd>\n<\/dl><\/dd>\n<dt>8.5&nbsp;&nbsp;Processing Big Data<\/dt><dd><dl>\n<dt>8.5.1&nbsp;&nbsp;Why It Is Hard -- Distributed Storage and Computation<\/dt>\n<dt>8.5.2&nbsp;&nbsp;Principles behind MapReduce<\/dt>\n<dt>8.5.3&nbsp;&nbsp;MapReduce for the Cloud<\/dt>\n<dt>8.5.4&nbsp;&nbsp;If It Can Go Wrong -- Resilience for Big Processing<\/dt>\n<\/dl><\/dd>\n<dt>8.6&nbsp;&nbsp;Data and Algorithms at Scale<\/dt><dd><dl>\n<dt>8.6.1&nbsp;&nbsp;Big Graphs<\/dt>\n<dt>8.6.2&nbsp;&nbsp;Time Series and Event Streams<\/dt><dd><dl>\n<dt>8.6.2.1&nbsp;&nbsp;Multi-scale with Mega-windows<\/dt>\n<dt>8.6.2.2&nbsp;&nbsp;Untangling Streams<\/dt>\n<dt>8.6.2.3&nbsp;&nbsp;Real-time Processing<\/dt>\n<\/dl><\/dd>\n<\/dl><\/dd>\n<dt>8.7&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\/accuracy\">accuracy<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/adversarial%20learning\">adversarial learning<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/alphago\">AlphaGo<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/apache%20hadoop\">Apache Hadoop<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/autonomous%20car\">autonomous car<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/backpropagation\">backpropagation<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/bias\">bias<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/big%20data\">big data<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/boosting\">boosting<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/cern\">CERN<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/cloud%20computation\">cloud computation<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/clustering\">clustering<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/combinatorial%20explosion\">combinatorial explosion<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/computer%20chess\">computer chess<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/convolutional%20neural%20network\">convolutional neural network<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/correlation%20matrix\">correlation matrix<\/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%20blue\">Deep Blue<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/deep%20neural%20network\">deep neural network<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/degrees%20of%20freedom%20%28data%29\">degrees of freedom (data)<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/dimension%20reduction\">dimension reduction<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/domain-specific%20knowledge\">domain-specific knowledge<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/ecg\">ECG <\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/eigenvector\">eigenvector<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/emotion\">emotion<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/ensemble%20methods\">ensemble methods<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/event\">event<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/event%20stream\">event stream<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/fault%20tolerant\">fault tolerant<\/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\/generalisation\">generalisation<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/generative%20adversarial%20network\">generative adversarial network<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/genes\">genes<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/genetic%20algorithm\">genetic algorithm<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/go\">Go<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/google\">Google<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/ground%20truth\">ground truth<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/higher-order%20function\">higher-order function<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/ibm\">IBM<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/image%20recognition\">image recognition<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/instabilities\">instabilities<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/kasparov%2C%20garry\">Kasparov, Garry<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/kernel\">kernel<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/least%20squares\">least squares<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/lee%20sedol\">Lee Sedol<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/linear%20regression\">linear regression<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/lisp\">Lisp<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/local%20data%20access\">local data access<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/locality\">locality<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/long-tail%20distribution\">long-tail distribution<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/machine%20learning\">machine learning<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/map\">map<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/mapreduce\">MapReduce<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/multi-dimensional%20scaling\">multi-dimensional scaling<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/n-gram\">n-gram<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/natural%20selection\">natural selection<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/neural%20network\">neural network<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/neural-network%20architecture\">neural-network architecture<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/non-linear%20transformations\">non-linear transformations<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/optimal\">optimal<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/overfitting\">overfitting<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/pagerank\">PageRank<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/parallel%20processing\">parallel processing<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/perceptron\">perceptron<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/pinch-point%20layer\">pinch-point layer<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/poorly%20constrained\">poorly constrained<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/pre-processing\">pre-processing<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/principal%20components%20analysis\">principal components analysis<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/python\">Python<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/quartile\">quartile<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/radial%20basis%20functions\">radial basis functions<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/random%20forest\">random forest<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/random%20segmentation\">random segmentation<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/rdf\">RDF<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/recommender%20systems\">recommender systems<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/reduce\">reduce<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/restricted%20boltzmann%20machine\">restricted Boltzmann machine<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/robotics\">robotics<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/robust%20to%20failure\">robust to failure<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/search%20space\">search space<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/segmentation\">segmentation<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/segmentation%20rule\">segmentation rule<\/a>, <strong><a href=\"https:\/\/alandix.com\/glossary\/aibook\/self%20learning\">self learning<\/a><\/strong>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/semantic%20web\">semantic web<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/sharding\">sharding<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/similarity%20measure\">similarity measure<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/social%20media\">social media<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/sparse%20matrix\">sparse matrix<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/standard%20deviation\">standard deviation<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/statistical%20techniques\">statistical techniques<\/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\/synthetic%20data\">synthetic data<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/time%20series\">time series<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/transpose\">transpose<\/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\/wavelet%20transform\">wavelet transform<\/a>, <a href=\"https:\/\/alandix.com\/glossary\/aibook\/windowing\">windowing<\/a><\/div>\n\n\n\n\n<\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":2,"featured_media":0,"parent":221,"menu_order":8,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_themeisle_gutenberg_block_has_review":false,"footnotes":""},"class_list":["post-243","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/pages\/243","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=243"}],"version-history":[{"count":3,"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/pages\/243\/revisions"}],"predecessor-version":[{"id":298,"href":"https:\/\/alandix.com\/aibook\/wp-json\/wp\/v2\/pages\/243\/revisions\/298"}],"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=243"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}