Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. Cited by. /N 100 Peter Bartlett's statistical learning theory course. Percy Liang. How can we explain the predictions of a black-box model? … His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers … 24. results. /Length 1337 … [, Mon 10/08: Lecture 5: Sub-Gaussian random variables, Rademacher complexity BAD 1 - 2 POOR 2 - 3 FAIR 3 - 4 GOOD 4 - 5. [, Wed 11/14: Lecture 16: FTRL in concrete problems: online regression & expert problem, convex to linear reduction His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers easier to communicate with through natural language. [, Thu 11/01: Homework 2 (uniform convergence), Mon 11/05: Lecture 13: Restricted Approximability, overview of Percy Liang is this you? His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers easier to communicate with through natural language. Select this result to view Percy Shuo Liang's phone number, address, and more. from MIT, 2004; Ph.D. from UC Berkeley, 2011). Home Percy Liang. AI Frontiers Conference brings together AI thought leaders to … Search Search. 2 0 obj << �R�[���8���ʵHaQ�W�ǁl�S����}�֓����]�HF��C#�F���/K����+��֮������#�I'ꉞ�'TcϽ�G�\�7�����-��m��}�;G����6�?�paC��i\�W.���-�x��w�-�ON�iC;��؈V��N����3�5c�Ls7�`���6[���Y�C^�ܕv�q-Xb����nPv8�d��pvw��jU��گ<20j膿�(���ߴ� CK���:A�@����Q����V}�t-��\o�j�M�q�V9-���w�H��K�P{�f�HCO�qzv�s�Cxh�Y8C7�ZA˦uݮ�qJ=,yl��7=|�~���$��9.F7.�Dxz��;��G�V���8|�[˝�U�q�:G|N��G/�ӈzLb��y�������Qh�j���w�{�{ �Ptƛi�x؋TLB�S�~�Ɇx��)��N|��a�OϾ{ ��DJ�O{��`�f �|�`��j7c&aƫO�$�9{���q�C�/��]�^��t�����/���� Percy Liang Author page based on publicly available paper data. Follow. Ms. Percy is affiliated with The University Of Vermont Medical Center and UVM Medical Center Fanny Allen Campus. As part of the Trustworthy ML Initiative's seminar series, Percy Liang (Stanford University) presents "Surprises in the Quest for Robust Machine Learning". Year; Squad: 100,000+ questions for machine comprehension of text. Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. Percy Liang is Lead Scientist at Semantic Machines and Assistant Professor of Computer Science at Stanford University. machine learning natural language processing. K�i���,% `) �Ԑ̀dR�i��t�o �l�Rl�M$Z�Ѱ��$1�)֔hXG���e*5�I��'�I��Rf2Gradgo"�4���h@E #- R x�-<>�)+��3e�M��t�`� [, Wed 11/28: Lecture 18: Multi-armed bandit problem in the If you identify any major omissions or other inaccuracies in the publication list, please let us know. Fp(t�� ��%4@@G���q�\ Percy Liang's 133 research works with 5,234 citations and 3,995 reads, including: Explore then Execute: Adapting without Rewards via Factorized Meta-Reinforcement Learning [, Wed 10/31: Lecture 12: Generalization and approximation in Understanding and Mitigating the Tradeoff Between Robustness and Accuracy Aditi Raghunathan * 1Sang Michael Xie Fanny Yang2 John C. Duchi 1Percy Liang … Current Students and Postdoctoral Researchers stream Boyd and Vandenberghe's Convex Optimization. from MIT, 2004; Ph.D. from UC Berkeley, 2011). endstream >> 122. papers. BAD GOOD. Dr. Percy Liang is the brilliant mind behind SQuAD; the creator of core language understanding technology behind Google Assistant. statistical learning theory course, Martin Wainwright's Overview, reviews, and comments on Percy Liang, mTurk Requester. Block user. offerings of this course, Peter Bartlett's statistical learning theory course, Boyd and --Massachusetts Institute of Technology, Dept. Percy Liang (Preferred) Suggest Name; Emails. real analysis, There is no required text for the course. Learn more about blocking users. stochastic setting If you notice any inaccuracies, please sign in and mark papers as correct or incorrect matches. >> Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. �8YX�.��?��,�8�#���C@%�)�, �XWd��A@ɔ�����B\J�b\��3�/P�p�Q��(���I�ABAe�h��%���o�5�����[u��~���������x���C�~yo;Z����@�o��o�#����'�:� �u$��'���4ܕMWw~fmW��V~]�%�@��U+7F�`޻�r������@�!�U�+G��m��I�a��,]����Ҳ�,�!��}���.�-��4H����+Wu����/��Z9�3qno}ٗ��n�i}��M�f��l[T���K B�Qa;�Onl���e����`�$~���o]N���". online learning [Please refer to, Mon 10/29: Lecture 11: Total variation distance, Wasserstein distance, Wasserstein GANs [. Ms. Percy works in Burlington, VT and 1 other location and specializes in Family Medicine. Bio Associate Professor in CS @Stanford @stanfordnlp | Pianist Lokasyon Stanford, CA Tweets 11 Followers 2,7K Following 197 Account created 31-10-2009 07:26:37 ID 86481377. Percy Liang. Percy Liang's course notes from previous offerings of this course. Free Instagram Followers [, Mon 11/26: Lecture 17: Multi-armed bandit problem, general OCO with partial observation You can help! [, Wed 11/07: Lecture 14: Online learning, online convex optimization, Follow the Leader (FTL) algorithm This information is crucial for deduplicating users, and ensuring you see your reviewing assignments. Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. Cited by. [, Wed 10/17: Lecture 8: Margin-based generalization error of Wassersetin GANs %���� stream Photos | Summary | Follow. and, Machine learning (CS229) or statistics (STATS315A), Convex optimization (EE364A) is recommended, Mon 09/24: Lecture 1: overview, formulation of prediction His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers easier to … hypothesis class [, Wed 10/03: Lecture 4: naive epsilon-cover argument, concentration inequalities Thompson Sampling [, Wed 10/24: Lecture 10: Covering techniques, overview of GANs /Filter /FlateDecode Bio. Enter email addresses associated with all of your current and historical institutional affiliations, as well as all your previous publications, and the Toronto Paper Matching System. Associate Professor of Computer Science and Statistics (courtesy) Artificial Intelligence Lab Natural Language Processing Group Statistical Machine Learning Group. Sort. from MIT, 2004; Ph.D. from UC Berkeley, 2011). His research spans theoretical machine learning to practical natural language processing; topics include semantic parsing, question answering, machine translation, online learning, method of moments, approximate inference, Bayesian modeling, and deep learning. A number of useful references: Percy Liang's course notes from previous He is an assistant professor of Computer Science and Statistics at Stanford University since 2012, and also the co-founder and renowned AI researcher of Semantic Machines, a Berkeley-based conversational AI startup acquired by Microsoft several months ago. View the profiles of professionals named "Percy Liang" on LinkedIn. of Electrical Engineering and Computer Science, 2005. Understanding and mitigating the tradeoff between robustness and accuracy.Aditi Raghunathan, Sang Michael Xie, Fanny Yang, John C. Duchi, Percy Liang.arXiv preprint arXiv:2002.10716, 2020. endobj This is Me - Control Profile. Verified email at cs.stanford.edu - Homepage. In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data, thereby identifying training points most responsible for a given prediction. #�;���$���J�Y����n"@����)|��Ϝ�L�?��!�H�&� ��D����@ %BHa�`�Ef�I�S��E�� �T Percy Liang, Computer Science Department, Stanford University/Statistics Department, Stanford University, My goal is to develop trustworthy systems that can communicate effectively with people and improve over time through interac. Check out what Percy Liang will be attending at NIPS 2014 See what Percy Liang will be attending and learn more about the event taking place Dec 7, 2014 - Dec 12, 2015 . My goal is to develop trustworthy systems that can communicate effectively with people and improve over time through interaction. Search for Percy Liang's work. Percy Liang Release 1.3 2012.07.24 Input: a sequence of words separated by whitespace (see input.txt for an example). Percy Liang. Sham Kakade's statistical learning theory course. problems, error decomposition [, Wed 09/26: Lecture 2: asymptotics of maximum likelihood estimators (MLE) [, Mon 10/01: Lecture 3: uniform convergence overview, finite two-layer neural networks The best result we found for your search is Percy Shuo Liang age 30s in Stanford, CA in the Stanford neighborhood. [, Mon 11/12: Lecture 15: Follow the Regularized Leader (FTRL) algorithm Approx. CS229T/STAT231: Statistical Learning Theory (Winter 2016) Percy Liang Last updated Wed Apr 20 2016 01:36 These lecture notes will be updated periodically as the course goes on. [, Mon 10/22: Lecture 9: VC dimension, covering techniques Percy Liang Thesis (M. from MIT, 2004; Ph.D. from UC Berkeley, 2011). 10, 2012 Percy Liang Google/Stanford [, Mon 10/15: Lecture 7: Rademacher complexity, neural networks Associate Professor of Computer Science, Stanford University. Percy Liang, 37 Palo Alto, CA. They have also lived in Palo Alto, CA and Berkeley, CA. � �T ��f��Ej͏���8���H��8f�@��)���@���D���W�a�\ ��G@Nb���� ��P� %PDF-1.5 /First 813 [, Wed 12/05: Lecture 20: Information theory, regret bound for Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. Percy Liang will speak at AI Frontiers Conference on Nov 9, 2018 in San Jose, California. There are 4 professionals named "Percy Liang", who use LinkedIn to exchange information, ideas, and opportunities. Reputation Score. /Length 1467 Jian Zhang 113 publications . Approximate Reputation Score. from MIT, 2004; Ph.D. from UC Berkeley, 2011). Home Research-feed … Associate Professor of Computer Science and Statistics. No matching publications found. One way to create this predictability is by taking advantage of machine learning. Block user Report abuse. probability theory, We are testing a new system for linking publications to authors. Implementation of the Brown hierarchical word clustering algorithm. 53. papers with code. x���o�6���+t��Z��.CV��=�;02c���#M�חI�q�6Z���N�h�����%-#�y��6��5d�)��D��H�qq�SL�"��. Previous years' home pages are, Uniform convergence (VC dimension, Rademacher complexity, etc), Implicit/algorithmic regularization, generalization theory for neural networks, Unsupervised learning: exponential family, method of moments, statistical theory of GANs, A solid background in Percy Liang. Vandenberghe's Convex Optimization, Sham Kakade's [, Mon 12/03: Lecture 19: Regret bound for UCB, Bayesian setup, Thompson sampling Percy is related to Zuyang L Liang and Ling Zhang as well as 1 additional person. Prevent this user from interacting with your repositories and sending you notifications. Sort by citations Sort by year Sort by title. Featured Co-authors. linear algebra, Learning Dependency-Based Compositional Semantics Semantic Representations for Textual Inference Workshop – Mar. xڥW�r�6}�W�����$;�t\7�N�c��_ �0�������H'�cStg, g���]��"�IEdH�(1$""#�HĚ�RI"!��HI� Gates 250 / pliang@cs.stanford.edu [Publications] Research. [, Wed 10/10: Lecture 6: Rademacher complexity, margin theory Percy Liang. Output: for each word type, its cluster (see output.txt for an example). Percy Liang percyliang. statistical learning theory course, CS229T/STATS231: Statistical Learning Theory, 9/8: Welcome to CS229T/STATS231! His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers easier to communicate with through natural language. /Type /ObjStm Tatsunori Hashimoto (Stanford University, post-doc, jointly supervised with Percy Liang, 2016{2019). Research Areas. Articles Cited by. 378 0 obj << Fanny Yang (Stanford University, post-doc, jointly supervised with Percy Liang, 2019). Join Facebook to connect with Percy Liang and others you may know. Percy Liang. : Percy Liang Skip slideshow. Rate Percy. View the profiles of people named Percy Liang. Assistant Professor of Computer Science, Stanford University. Martin Wainwright's statistical learning theory course Block or report user Block or report percyliang. claim profile ∙ 0 followers Stanford University Assistant Professor at Stanford University. Eng.) How Should We Evaluate Machine Learning for AI? /Filter /FlateDecode Percy Liang, Assistant Professor of Computer Science at Stanford University, explains that humans rely on some degree of predictability in their day-to-day interactions — both with other humans and automated systems (including, but not limited to, their cars). 0.00 5.00 /5. Michael I. Jordan 185 publications . Includes bibliographical references (p. 75-82). Title.