=== Syllabus ===

^ Lect. ^ Lecturer ^ Topic ^ Pdf ^ Additional reading ^
| 01 | BF | Markov Random Fields & Gibbs Random Fields | {{:courses:xep33sml:materials:lecture_01.pdf| }}| |
| 02 | BF | The most probable realisation of a GRF | {{:courses:xep33sml:materials:lecture_02.pdf| }}| [[https://www.nowpublishers.com/article/Details/CGV-084| [Savchynskyy19] ]] |
| 03 | BF | Belief Networks & Stochastic Neural Networks| {{:courses:xep33sml:materials:lecture_03.pdf| }}| {{:courses:xep33sml:materials:neal-connectionist_learning_of_belief_networks-1992.pdf| [Neal92]}}, [[https://arxiv.org/abs/1401.4082| Rezende, 2014]], [[https://arxiv.org/abs/1312.6114 | Kingma, 2013]] |
| 04 | VF | Empirical Risk Minimization | {{ :courses:xep33sml:materials:lecture_erm_ls2020.pdf | }}, print {{ :courses:xep33sml:materials:lecture_erm_ls2020_print.pdf | }} | [[https://people.cs.umass.edu/~domke/courses/sml2010/10theory.pdf| [Domke10] ]] [[https://www.shivani-agarwal.net/Teaching/E0370/Aug-2011/Lectures/10.pdf|[Agarwal11]]] [[http://www.cs.cmu.edu/~ninamf/ML11/lect1115.pdf|[Balcan11]]] |
| 05 | VF | Structured Output Linear Classifier and Perceptron| {{ :courses:xep33sml:materials:lecture_perceptron_ls2020.pdf | }}, print {{ :courses:xep33sml:materials:lecture_perceptron_ls2020_print.pdf | }} | [[https://www.aclweb.org/anthology/W02-1001/|[Collins02]]] {{ :courses:xep33sml:materials:perceptron_proof.pdf |Peceptron proof}} |
| 06 | VF | Learning max-sum classifier by Perceptron | {{ :courses:xep33sml:materials:lecture_maxsumperceptron_ls2020.pdf | }}, print {{ :courses:xep33sml:materials:lecture_maxsumperceptron_ls2020_print.pdf | }} | [[http://www.jmlr.org/papers/v9/franc08a.html|[Franc08]]] |
| 07 | VF | Structured Output Support Vector Machines | {{ :courses:xep33sml:materials:lecture_sosvm_ls2020.pdf | }}, print {{ :courses:xep33sml:materials:lecture_sosvm_ls2020_print.pdf | }}  | [[http://www.jmlr.org/papers/v6/tsochantaridis05a.html|[Tsochantaridis05]]]|
| 08 | VF |Cutting Plane Algorithm | {{ :courses:xep33sml:materials:lecture_cpa_ls2020.pdf | }}, print {{ :courses:xep33sml:materials:lecture_cpa_ls2020_print.pdf | }} | [[http://www.jmlr.org/papers/v11/teo10a.html|[Teo09]]]|
| 09 | VF | Learning Max-Sum classifier by SO-SVM  | {{ :courses:xep33sml:materials:lecture_sosvm4maxsum_ls2020.pdf | }}, print {{ :courses:xep33sml:materials:lecture_sosvm4maxsum_ls2020_print.pdf | }} | [[ https://papers.nips.cc/paper/2397-max-margin-markov-networks.pdf|[Taskar04]]] [[https://dl.acm.org/doi/10.1145/1015330.1015444|[Taskar04]]] [[http://www.jmlr.org/papers/v9/franc08a.html|[Franc08]]]|
| 10 | BF | Maximum Likelihood learning for MRFs I |{{ :courses:xep33sml:materials:lecture_10.pdf | }} | [[ https://www.elsevier.com/books/submodular-functions-and-optimization/fujishige/978-0-444-52086-9|[Fujishige (book)]]], [[https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Zhang_Higher-Order_Inference_for_ICCV_2015_paper.pdf|[Zhang2015]]]|
| 11 | BF | Maximum Likelihood learning for MRFs II | {{ :courses:xep33sml:materials:lecture_11.pdf | }}| |
| 12 | BF | Variational Bayesian inference for DNNs | {{ :courses:xep33sml:materials:bayes-inf.pdf | }}| |
| 13 | BF | Variational Autoencoders | {{ :courses:xep33sml:materials:vae.pdf | }}|[[https://arxiv.org/abs/1606.05908|[Doersch2016]]] |
| 14 | BF | Generative adversarial networks | {{ :courses:xep33sml:materials:gans.pdf | }}| [[https://arxiv.org/abs/1701.07875|[Arjovsky2017]]] |