{"id":1366,"date":"2021-04-13T12:50:52","date_gmt":"2021-04-13T12:50:52","guid":{"rendered":"http:\/\/yingzhenli.net\/home\/en\/?page_id=1366"},"modified":"2022-04-04T21:45:00","modified_gmt":"2022-04-04T21:45:00","slug":"teaching","status":"publish","type":"page","link":"https:\/\/yingzhenli.net\/home\/en\/?page_id=1366","title":{"rendered":"Teaching"},"content":{"rendered":"\n<p class=\"has-medium-font-size wp-block-paragraph\"><a href=\"https:\/\/www.imperial.ac.uk\/computing\/current-students\/courses\/70015\/\" target=\"_blank\" rel=\"noreferrer noopener\">Mathematics for Machine Learning (Autumn 2021 @ Imperial)<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Gradient descent (GD) [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_gradient_descent_notes.pdf\" target=\"_blank\">notes<\/a>]<ul><li>constant step-size GD, convergence analysis [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_gradient_descent1.pdf\" target=\"_blank\">slides<\/a>]<\/li><li>Advanced techniques &amp; SGD [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_gradient_descent2.pdf\" target=\"_blank\">slides<\/a>]<\/li><\/ul><\/li><li>Ridge regression [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_regression_pca_notes.pdf\" target=\"_blank\">notes<\/a>]<ul><li>bias-variance trade-off [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_ridge_regression.pdf\" target=\"_blank\">slides<\/a>]<\/li><\/ul><\/li><li>Principal component analysis (PCA) [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_regression_pca_notes.pdf\" target=\"_blank\">notes<\/a>]<ul><li>minimum reconstruction error view [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_pca1.pdf\" target=\"_blank\">slides<\/a>]<\/li><li>maximum variance view [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_pca2.pdf\" target=\"_blank\">slides<\/a>]<\/li><\/ul><\/li><li>Constrained optimisation <ul><li>PCA [<a href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_constrained_opt1.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">slides<\/a>][<a href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_constrained_opt_notes.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">notes<\/a>]<\/li><li>Ridge regression [<a href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_constrained_opt2.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">slides<\/a>]<\/li><\/ul><\/li><li>The kernel trick [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_kernel.pdf\" target=\"_blank\">slides<\/a>][<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_mmlcourse2021_kernel_notes.pdf\" target=\"_blank\">notes<\/a>]<\/li><\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n\n\n\n<p class=\"has-medium-font-size wp-block-paragraph\"><a rel=\"noreferrer noopener\" href=\"http:\/\/wp.doc.ic.ac.uk\/bkainz\/teaching\/70010-deep-learning\/\" target=\"_blank\">Deep Learning (Winter 2022 @ Imperial)<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Generative models<ul><li>Intro to generative modelling [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_gen_models_intro.pdf\" target=\"_blank\">slides<\/a>]<\/li><li>Variational auto-encoders [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_vae_basics.pdf\" target=\"_blank\">slides<\/a>] [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_vae_notes.pdf\" target=\"_blank\">notes<\/a>]<\/li><li>Generative adversarial networks [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_gan_basics.pdf\" target=\"_blank\">slides<\/a>] [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2021_gan_notes.pdf\" target=\"_blank\">no<\/a><a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_gan_notes.pdf\" target=\"_blank\">t<\/a><a href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_gan_notes.pdf\" target=\"_blank\" rel=\"noreferrer noopener\">es<\/a>]<\/li><li>Recent advances in deep generative models [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_gen_models_applications.pdf\" target=\"_blank\">slides<\/a>]<\/li><\/ul><\/li><li>RNNs<ul><li>Intro to RNNs\/LSTMs [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_rnn_basics.pdf\" target=\"_blank\">slides<\/a>] [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_rnn_notes.pdf\" target=\"_blank\">notes<\/a>]<\/li><li>Applications (e.g. Seq2Seq) [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_rnn_applications.pdf\" target=\"_blank\">slides<\/a>]<\/li><\/ul><\/li><li>Attention networks<ul><li>Attention basics &amp; Transformer [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_attention_basics.pdf\" target=\"_blank\">slides<\/a>] [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_attention_notes.pdf\" target=\"_blank\">notes<\/a>]<\/li><li>Recent advances in attention methods [<a rel=\"noreferrer noopener\" href=\"http:\/\/yingzhenli.net\/home\/pdf\/imperial_dlcourse2022_attention_applications.pdf\" target=\"_blank\">slides<\/a>]<\/li><\/ul><\/li><\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Mathematics for Machine Learning (Autumn 2021 @ Imperial) Gradient descent (GD) [notes] constant step-size GD, convergence analysis [slides] Advanced techniques &amp; SGD [slides] Ridge regression [notes] bias-variance trade-off [slides] Principal component analysis (PCA) [notes] minimum reconstruction error view [slides] maximum variance view [slides] Constrained optimisation PCA [slides][notes] Ridge regression [slides] The kernel trick [slides][notes] Deep ... <span class=\"more\"><a class=\"more-link\" href=\"https:\/\/yingzhenli.net\/home\/en\/?page_id=1366\">[Read more...]<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["entry","page","publish","author-admin","post-1366"],"_links":{"self":[{"href":"https:\/\/yingzhenli.net\/home\/en\/index.php?rest_route=\/wp\/v2\/pages\/1366","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/yingzhenli.net\/home\/en\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/yingzhenli.net\/home\/en\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/yingzhenli.net\/home\/en\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/yingzhenli.net\/home\/en\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1366"}],"version-history":[{"count":18,"href":"https:\/\/yingzhenli.net\/home\/en\/index.php?rest_route=\/wp\/v2\/pages\/1366\/revisions"}],"predecessor-version":[{"id":1509,"href":"https:\/\/yingzhenli.net\/home\/en\/index.php?rest_route=\/wp\/v2\/pages\/1366\/revisions\/1509"}],"wp:attachment":[{"href":"https:\/\/yingzhenli.net\/home\/en\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1366"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}