How Did I Get Here?
Who am I?
Jun Zhu2011 present Associate Professor, State Key Lab ofIntelligent Technology and Systems, Department ofComputer Science and Technology, Tsinghua thu.net/ jun
Education、Working and VisitingExperience01 05 Tsinghua, B.E05 07 Tsinghua, M. E05 09 Tsinghua, PhD07 09 CMU Visiting Researcher09 11 CMU Post-doc Fellow10. 2 10.3 & 10 Stanford VisitingResearcherCMU. Stanford04 07 MSRA, Research Internon joint projects
Structured Learning Maximum Entropy Discrimination Markov Network (MaxEnDNet) – a novel framework with sound theoretical guarantee;– generalizes to latent factor models and non-parametric Bayesian inference.Learning PrinciplesClassificationStructured PredictionMax-Likelihood Estimation (Joint)Naïve BayesHMMs (Math. Stat.,1966)Max-Likelihood Est. (Conditional)Logistic RegressionCRFs (ICML, 2001)Support Vector MachinesMax-Margin MNs (NIPS, 2003)Max-Entropy DiscriminationMaxEnDNet (ICML, 2008)Max-Margin LearningMax-Entropy Discrimination LearningMaxEnDNetTheoryLatent VariableModels Representative PublicationsNon-parametricBayesian– Theoretical guarantee (JMLR 2009, ICML 2008, ICML 2009a);– Latent factor models (NIPS 2008, ICML 2009b, ICML 2010, NIPS 2010a,b,JMLR 2011, PAMI 2011);– Non-parametric Bayesian (ICML 2011, 2012, NIPS, 2012).
Structured Learning Regularized (Nonparametric) Bayesian InferenceMax-margin Supervised Topic Models(Zhu et al., JMLR’12; Jiang, Zhu, et al., NIPS’12)Infinite Latent SVMs(Zhu, Chen & Xing, NIPS’11)V’U XYNonparametric Relational ModelsNonparametric Matrix Factorization(Zhu, ICML’12)(Xu, Zhu, & Zhang, NIPS’12)
Structured Learning Sparse High-dimensional Learning – fast algorithms for feature selection and structure learning of Markov networks;– adaptive multi-task learning with rich features;Lasso– sparse topical coding.JSTOR, 1996Compressed SensingIEEE Trans. IT, 2004Sparse Highdim LearningLearning MNStructureMulti-taskLearning Representative PublicationsSparse CodingNature, 1996Sparse TopicalCoding– Structure learning of Markov networks (NIPS 2010c, SIGKDD 2009a,SIGKDD 2010);– Multi-task learning (NIPS 2010d);– Sparse topical coding (UAI 2011, SIGKDD 2011).
Practical Applications Statistical Web Data Mining – a novel statistical modeling framework for robust web data extraction;– bootstrapping for entity-relationship mining;– probabilistic graphical models for social network analysis.Web ipMining Representative PublicationsSocialNetworkAnalysis– Information extraction (ICML 2005, SIGKDD 2006, SIGKDD 2007, ICML2007, JMLR 2008, WWW 2009a);– Entity relationship mining (WWW 2009b);– Social network analysis (SIGKDD 2009b).
How Did I Get Here?where “I Jun Zhu”
How Did I Get Here (Tianjin)? Thanks MSRA and
How Did I Get the Talk Title? The credits go to
How Did I Get My Career? Successful undergraduate researchtraining on CPU design and hardwareConfidencePersistenceWikibooks But, my heart leads me to AI andCredit:ML forgraduate study and the career
How Did I Get to MSRA? A random chance for 0.5 year internship but, turn out to be 3 Years! very fruitful and enjoyable time
How Did I Get to CMU? 2007, sponsored visit by the government 2008, invited visit by CMU 2009, post-doc & project scientist withSailing Lab
How Did I Get back to Tsinghua? Persuaded by Professor Bo Zhang to believein the bright future Get the job offer after an interview Back to Tsinghua without looking for otherplaces
How Did I Get the 973 Project? Probably the youngest team leader in 973projects Thanks to my team members Special thanks to ProfessorZongben Xu (Member of CAS)for “not just selecting for titles”
How Did I Get to the Future? Never! Grammar mistakes!
How Will I Get to the Future? Hard! The future is uncertain, my long marchjust starts I’ll follow my heart, be confident, bepersistent, and try all the best
Acknowledgements Advisor: Prof. Bo Zhang Mentors & Collaborators: Dr. Zaiqing Nie、Dr. Ji-Rong Wen、Dr. Lei Zhang、Dr. Wei-Ying Ma (MSRA) Prof. Eric P. Xing (CMU)、Prof. Li Fei-Fei (Stanford) Amr Ahmed (CMU), Ning Chen (Tsinghua), Ni Lao (CMU), Seunghak Lee(CMU), Li-jia Li (Stanford), Xiaojiang Liu (USTC), Xiaolin Shi (Stanford), HaoSu (Stanford), Yuandong Tian (CMU) , Matt Wytock (CMU).Students: Aonan Zhang, Minjie Xu, Hugh PerkinsWei Li, Bei Chen, Kuan Liu.Funding:
-Non-parametric Bayesian (ICML 2011, 2012, NIPS, 2012). Theory Non-parametric Bayesian Latent Variable Models MaxEnDNet Learning Principles Classification Structured Prediction Max-Likelihood Estimation (Joint) Naïve Bayes HMMs (Math. Stat.,1966) Max-Likelihood Est. (Conditional) Logistic Regression CRFs (ICML, 2001)
Texts of Wow Rosh Hashana II 5780 - Congregation Shearith Israel, Atlanta Georgia Wow ׳ג ׳א:׳א תישארב (א) ׃ץרֶָֽאָּהָּ תאֵֵ֥וְּ םִימִַׁ֖שַָּה תאֵֵ֥ םיקִִ֑לֹאֱ ארָָּ֣ Îָּ תישִִׁ֖ארֵ Îְּ(ב) חַורְָּ֣ו ם
speakoutTIP The verb get has more than twenty meanings in English! It can mean ‘become’ (get hungry), ‘arrive’ (get home), ‘obtain’ (get a job), ‘buy’ (get a new car) and is in many phrases: get up, get on a plane, get dressed. When you hear or see the word get, think about which meaning it has. Which meaning does get have in these
Why was the Roman Empire important? VII. Why did Hadrian build his wall VIII. Who was in the Roman army? IX. How did Roman Britain defend itself? X. What did the Romans build in Britain? XI. How did the Romans? XII. What was life like for a Roman family? XIII. What did the Romans believe in? XIV. What happened to Roman Britain? 1 What was Britain like before the Romans? Celtic Times Did you .
Illuminati on my heels so I got to run And I’ll never stop until that hill is what my mom is on Why did Aliyah take that plane? Why did Left Eye get in that lane? Why did Tupac go to the Veg[as]? Why did Big go back to L.A.? Damn, damn/Why did Pimp C pick up that drink? When Mike Jack died I
Crush It - Cart Card. Crush It - Cart Card with Club Name. PRINT. Cart Cards. Place these in your carts during prime sign up seasons. Contact us today! 000.000.0000 firstname.lastname@example.org. Introducing a Golf Program for Life. Copy here copy here copy here copy here copy here copy here co
3. Did you make any job easier or more efficient? 4. Did you train anyone? 5. Did you implement a new procedure or system? 6. Did you do a job with fewer people? 7. Did you do a job in less time than before? 8. Were you asked to do a special project? Take on new responsibilities?
13.What was the Hampton Roads drama? 14. What did Section 1 of the 13th amendment do? 15.What did Section 2 of the 13th amendment do? 16.What did the Civil Rights Act of 1866 accomplish? 17. What did Congress require of the former Confederate states? 18.What did th
Jim Rohn: The Keys To Success Book Summary CLICK HERE FOR THE Written Summary CLICK HERE FOR THE YouTube Summary CLICK HERE FOR THE Audio Podcast Summary CLICK HERE TO BUY THE BOOK CLICK HERE TO Follow us on Instagram CLICK HERE TO Subscribe to our Weekly Book Summary Newsletter .
I am here, I am waiting, I am praying I am here, on my phone, reading my bible I am here, on Zoom, praying for the preacher I am here, anonymous, listening to God I am here, at the pulpit, meeting eyes and the camera lens We are here, the Church Triumphant, joining your praise We
World Refugee Day posters (download here) GIPHY stickers (access here) Social media assets (access here) Use the #WorldRefugeeDay hashtag on Twitter to activate the WRD emoji Package of photos (access here) Videos about the power of inclusion (access here) World Refugee Day live blog (link here)
Global Medical Device Podcast (GreenLight.Guru) here, Mike on MedTech (Medical Product Outsourcing) here, Medical Design and Outsourcing here, Guerilla Regulatory Strategy (MED Device Online) here and Healthcare Packaging here or LinkedIn here. Presenter Bio Michael Drues, Ph.D., is a regulatory strategy consultant specializing in designing novel
Underscore.js: This is the only hard dependency which needs to be included. You can get it from here. jQuery.js: Include this file for RESTful persistence, history support via Backbone.Router and DOM manipulation with Backbone.View. You can get it from here. json2.js: Include this file for older Internet Explorer support. You can get it from here.
What did they get right and what did they get wrong? We begin with the origins of the euro and the roots of the crisis, before turning to attempts to deal with it in 2010 and thereafter. What German ordoliberalism got right at the birth of the euro German ordoliberals got some things right when the terms of European Economic
Did You Get It? Presentación de vocabulario Clothing † Study the words that are used to talk about clothing and the way they ﬁ t. Clothes vestirse (to get dressed) las botas (boots) las sandalias (sandals) el suéter (sweater) la pulsera (bracelet) el traje (suit) la falda (skirt) la
The Adventures of Tom Sawyer Book/CD-Rom Pack by (author) Mark Twain, Jennifer Bassett (Series Editor), (9780194789004) Oxford Bookworms Library, Stage 1 (2008) 1a Tom and his Friends. 1. Who was calling Tom? 2. Where did Aunt Polly look first? 3. Where did she look next? 4. What did Tom try to do? 5. What did he have in his pocket? 6. Tom said, “Quick , _ _ _”. 7. Was Aunt .
submissions. This guide covers the application of the DID, how to tailor the DID in the Contract Data Requirements List (CDRL), and clarification on the intent of the DID. This guide is applicable to all OSD contracts with a requirement for the Integrated Program Management Report (IPMR) Data Item Description (DID) DI-MGMT-81861A.
MINISTRY: JUSTICE & SERVICE “ Truly I tell you, just as you did it to one of the least of these you did it to Me Just as you did not do it to one of the least of these, you did not do it to me.” (Matthew 25:40) The Peer Minister for Justice & Service focuses on serving those in need by organizing and
World War 1. 6. When did European countries partition the Middle East? After the breakup of the Ottoman Empire at the end of WW1. 7. How did the way that the Middle East was divided lead to regional conflict? The British and French did not take into account the ethnic and religious differences in SW Asia which led to "regional conflict"
almost) – but we did organise tours using those ancient methods of the phone call and the post. When I look back it’s difficult to imagine how we did what we did, but it all did happen, mostly without calamity, reasonably efficiently, and quite extensively. We
2) One day a spider met a fly. a) How many legs did they have altogether? b) How many legs and eyes did they have altogether? c) How many more legs did the spider have than letters in ‘spider’? d) How many more legs did the fly have than letters in ‘fly’? 3) Susie is 8 years ol