{"id":20,"date":"2014-01-29T14:45:50","date_gmt":"2014-01-29T13:45:50","guid":{"rendered":"http:\/\/deep-learning.compute.dtu.dk\/?page_id=20"},"modified":"2014-08-21T12:47:43","modified_gmt":"2014-08-21T11:47:43","slug":"lectures","status":"publish","type":"page","link":"http:\/\/deep-learning.compute.dtu.dk\/?page_id=20","title":{"rendered":"Lectures"},"content":{"rendered":"<style type=\"text\/css\"><!--\ntable,th,td{ border: 1px solid grey;} p{margin:0} td {text-align: left; vertical-align: top;}\n--><\/style>\n<h2>Lecturers<\/h2>\n<ul>\n<li><a href=\"http:\/\/www.dmi.usherb.ca\/~larocheh\/index_en.html\">Hugo Larochelle<\/a><\/li>\n<li><a href=\"http:\/\/compute.dtu.dk\/~lkai\">Lars Kai Hansen<\/a><\/li>\n<li><a href=\"http:\/\/image.diku.dk\/igel\/\">Christian Igel<\/a><\/li>\n<li><a href=\"http:\/\/aaroncourville.wordpress.com\">Aaron Courville<\/a><\/li>\n<li><a href=\"http:\/\/www.idsia.ch\/~ciresan\/\">Dan Claudiu Cire\u0219an<\/a><\/li>\n<\/ul>\n<h2>Slides<\/h2>\n<table>\n<tbody>\n<tr>\n<td>Introduction to neural networks &#8211;\u00a0Lars Kai Hansen<\/td>\n<td>[wpdm_file id=6]<\/td>\n<\/tr>\n<tr>\n<td>Markov Random Fields and Restricted Boltzmann Machines &#8211;\u00a0Christian Igel<\/td>\n<td>[wpdm_file id=7]<\/td>\n<\/tr>\n<tr>\n<td>Unsupervised feature learning &#8211;\u00a0Hugo Larochelle<\/td>\n<td>[wpdm_file id=5]<\/td>\n<\/tr>\n<tr>\n<td>Modern deep architectures &#8211;\u00a0Aaron Courville<\/td>\n<td>[wpdm_file id=10]<\/td>\n<\/tr>\n<tr>\n<td>Dan Claudiu Cire\u0219an &#8211; Convolutional neural networks<\/td>\n<td>[wpdm_file id=11]<\/td>\n<\/tr>\n<tr>\n<td>Deep learning in breast cancer screening &#8211;\u00a0Michiel Kallenberg<\/td>\n<td>[wpdm_file id=9l]<\/td>\n<\/tr>\n<tr>\n<td>Deep learning lessons from image, text and bioinformatics applications &#8211;\u00a0Ole Winther<\/td>\n<td>[wpdm_file id=8l]<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Practical sessions<\/h2>\n<table>\n<tbody>\n<tr>\n<td>Restricted Boltzmann Machines in Shark<\/td>\n<td>[UPDATE 15\/08] <a href=\"http:\/\/deep-learning.compute.dtu.dk\/wp-content\/uploads\/2014\/01\/Installation_instructions_Shark.pdf\">Installation instructions (pdf)<\/a><\/td>\n<td>[UPDATE 15\/08] <a href=\"http:\/\/deep-learning.compute.dtu.dk\/wp-content\/uploads\/2014\/01\/SharkRBM.zip\">Code Shark RBM (zip)<\/a><\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>Autoencoders for unsupervised pre-training<\/td>\n<td><a href=\"http:\/\/deep-learning.compute.dtu.dk\/wp-content\/uploads\/2014\/08\/Instructions_installation_session_unsupervised_learning.pdf\">Installation instructions (pdf)<\/a><\/td>\n<td>Linux\/Mac: [wpdm_file id=2]<\/td>\n<td>Windows: [wpdm_file id=4]<\/td>\n<\/tr>\n<tr>\n<td>Convolutional neural networks for digit recognition<\/td>\n<td><\/td>\n<td>Linux\/Mac: [wpdm_file id=12]<\/td>\n<td>Windows: [wpdm_file id=13]<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Suggested reading<\/h2>\n<h6><strong>Introduction to neural networks<\/strong><\/h6>\n<ul>\n<li>Chapter 11 in <a href=\"http:\/\/statweb.stanford.edu\/~tibs\/ElemStatLearn\/printings\/ESLII_print10.pdf\">The Elements of Statistical Learning<\/a>, Hastie et al., 2013<\/li>\n<li>Chapter 4 &amp; 5 in\u00a0<a href=\"http:\/\/research.microsoft.com\/en-us\/um\/people\/cmbishop\/prml\/index.htm\">Pattern Recognition and Machine Learning<\/a>.<a title=\"Pattern Recognition and Machine Learning\" href=\"http:\/\/research.microsoft.com\/en-us\/um\/people\/cmbishop\/prml\/index.htm\"><br \/>\n<\/a><\/li>\n<li><a href=\"http:\/\/eprints.aston.ac.uk\/639\/1\/NCRG_96_001.pdf\">Neural networks: a pattern recognition perspective<\/a>, Bishop, 1996.<\/li>\n<li>Lecture 1 &amp; 2 in Hugo Larochelle&#8217;s <a href=\"http:\/\/info.usherbrooke.ca\/hlarochelle\/neural_networks\/content.html\">course on neural networks<\/a>.<\/li>\n<\/ul>\n<h6><strong>Markov Random Fields and Restricted Boltzmann Machines<\/strong><\/h6>\n<ul>\n<li><a href=\"http:\/\/image.diku.dk\/igel\/paper\/TRBMAI.pdf\">Training Restricted Boltzmann Machines: An Introduction<\/a>,\u00a0Fischer and Igel, 2014<\/li>\n<li><a href=\"http:\/\/www.nowozin.net\/sebastian\/papers\/nowozin2011structured-tutorial.pdf\">Structured Learning and\u00a0Prediction in Computer Vision<\/a>, Nowozin and Lampert, 2011<\/li>\n<\/ul>\n<h6><strong>Unsupervised feature learning<\/strong><\/h6>\n<ul>\n<li><a href=\"http:\/\/www.cs.toronto.edu\/~hinton\/science.pdf\">Reducing the dimensionality of data with neural networks<\/a>, Hinton and\u00a0Salakahutdinov, 2006<\/li>\n<li><a href=\"http:\/\/web.stanford.edu\/class\/cs294a\/sparseAutoencoder.pdf\">Sparse autoencoder tutorial<\/a>, Andrew Ng<\/li>\n<li><a href=\"http:\/\/www.iro.umontreal.ca\/~vincentp\/Publications\/denoising_autoencoders_tr1316.pdf\">Extracting and Composing Robust Features with Denoising<\/a><br \/>\n<a href=\"http:\/\/machinelearning.org\/archive\/icml2008\/papers\/592.pdf\">Autoencoders<\/a>, Vincent et al., 2008<\/li>\n<\/ul>\n<h6><strong>Modern deep architectures<\/strong><\/h6>\n<ul>\n<li><a href=\"http:\/\/www.utstat.toronto.edu\/~rsalakhu\/papers\/dbm.pdf\">Deep Boltzmann Machines<\/a>,\u00a0Salakhutdinov and Hinton, 2009<\/li>\n<li><a href=\"http:\/\/arxiv.org\/abs\/1207.0580\">Improving neural networks by preventing co-adaptation of feature detectors<\/a>, Hinton et al, 2012<\/li>\n<li><a href=\"http:\/\/arxiv.org\/pdf\/1302.4389v4.pdf\">Maxout networks<\/a>, Goodfellow et al, 2013<\/li>\n<li><a href=\"http:\/\/jmlr.org\/papers\/volume11\/erhan10a\/erhan10a.pdf\">Why Does Unsupervised Pre-training Help Deep Learning?<\/a>,\u00a0Erhan et al., 2010<\/li>\n<li><a href=\"http:\/\/arxiv.org\/pdf\/1312.6114v10.pdf\">Auto-Encoding Variational Bayes<\/a>, Kingma et al., 2014<\/li>\n<\/ul>\n<h6><strong>Convolutional neural networks<\/strong><\/h6>\n<ul>\n<li><a href=\"http:\/\/yann.lecun.com\/exdb\/publis\/pdf\/jarrett-iccv-09.pdf\">What is the Best Multi-Stage Architecture for Object Recognition?<\/a>, Jarrett et al., 2009<\/li>\n<li><a href=\"http:\/\/papers.nips.cc\/paper\/4824-imagenet-classification-with-deep-convolutional-neural-networks\">ImageNet Classification with Deep Convolutional Neural Networks<\/a>, Krizhevsky et al., 2012<\/li>\n<li><a href=\"http:\/\/www.cs.toronto.edu\/~rgrosse\/icml09-cdbn.pdf\">Convolutional Deep Belief Networks<\/a><a href=\"http:\/\/www.cs.toronto.edu\/~rgrosse\/icml09-cdbn.pdf\">for Scalable Unsupervised Learning of Hierarchical Representations<\/a>, Lee et al. 2009<\/li>\n<li><a href=\"http:\/\/www.idsia.ch\/~ciresan\/data\/cvpr2012.pdf\">Multi-column Deep Neural Networks for Image Classification,\u00a0Cire\u0219an<\/a> et al., 2012<\/li>\n<\/ul>\n<h2>Further reading<\/h2>\n<ul>\n<li><a href=\"http:\/\/www.iro.umontreal.ca\/~bengioy\/papers\/ftml_book.pdf\">Learning Deep Architectures for AI<\/a>, Bengio, 2009<\/li>\n<li>Hugo Larochelle&#8217;s <a href=\"http:\/\/info.usherbrooke.ca\/hlarochelle\/neural_networks\/content.html\">class on neural networks<\/a>.<\/li>\n<li>Geoffrey Hinton&#8217;s <a href=\"https:\/\/www.coursera.org\/course\/neuralnets\">Coursera class on neural networks<\/a><\/li>\n<li>deeplearning.net:\u00a0<a href=\"http:\/\/deeplearning.net\/reading-list\/\">reading list<\/a>\u00a0and\u00a0<a href=\"http:\/\/deeplearning.net\/tutorial\/\">tutorial<\/a>.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Lecturers Hugo Larochelle Lars Kai Hansen Christian Igel Aaron Courville Dan Claudiu Cire\u0219an Slides Introduction to neural networks &#8211;\u00a0Lars Kai Hansen [wpdm_file id=6] Markov Random Fields and Restricted Boltzmann Machines &#8211;\u00a0Christian Igel [wpdm_file id=7] Unsupervised feature learning &#8211;\u00a0Hugo Larochelle [wpdm_file id=5] Modern deep architectures &#8211;\u00a0Aaron Courville [wpdm_file id=10] Dan Claudiu Cire\u0219an &#8211; Convolutional neural networks &hellip; <a href=\"http:\/\/deep-learning.compute.dtu.dk\/?page_id=20\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">Lectures<\/span> <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":3,"featured_media":0,"parent":0,"menu_order":3,"comment_status":"closed","ping_status":"open","template":"","meta":{"footnotes":""},"class_list":["post-20","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"http:\/\/deep-learning.compute.dtu.dk\/index.php?rest_route=\/wp\/v2\/pages\/20","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/deep-learning.compute.dtu.dk\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/deep-learning.compute.dtu.dk\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/deep-learning.compute.dtu.dk\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"http:\/\/deep-learning.compute.dtu.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=20"}],"version-history":[{"count":54,"href":"http:\/\/deep-learning.compute.dtu.dk\/index.php?rest_route=\/wp\/v2\/pages\/20\/revisions"}],"predecessor-version":[{"id":362,"href":"http:\/\/deep-learning.compute.dtu.dk\/index.php?rest_route=\/wp\/v2\/pages\/20\/revisions\/362"}],"wp:attachment":[{"href":"http:\/\/deep-learning.compute.dtu.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=20"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}