from MIT, 2004; Ph.D. from UC Berkeley, 2011). share, Influence functions estimate the effect of removing particular training ∙ share, We tackle the problem of generating a pun sentence given a pair of homop... 0 ∙ share, Though machine learning algorithms excel at minimizing the average loss ... 11/02/2018 ∙ by Aditi Raghunathan, et al. ∙ Percy Liang 103 publications . 06/29/2020 ∙ by Sang Michael Xie, et al. The dataset was presented by researchers: Pranav Rajpurkar and Jian Zhang and Konstantin Lopyrev and Percy Liang from Stanford University. share, Convex relaxations have emerged as a promising approach for verifying share, How can we measure whether a natural language generation system produces... ∙ 05/20/2020 ∙ by Michihiro Yasunaga, et al. Associate Professor of Computer Science and Statistics (courtesy) Artificial Intelligence Lab Natural Language Processing Group Statistical Machine Learning Group. 121, Computational principles of intelligence: learning and reasoning with ∙ STAT 205 Probability Theory Fall 2006 Topic: Inversion formula Lecturer: Jim Pitman, Scribe: Bo Li, Ankit Jain, Percy Liang, Editor: ∙ 8 Percy Liang (Stanford+CodaLab) Victoria Stodden (UIUC) Joaquin Vanschoren (TU/e+OpenML). ∙ 11/16/2020 ∙ by Yu Gu, et al. S.Sankara has 1 job listed on their profile. experimen... co... Prefix-Tuning: Optimizing Continuous Prompts for Generation, WILDS: A Benchmark of in-the-Wild Distribution Shifts, In-N-Out: Pre-Training and Self-Training using Auxiliary Information for 0 Hi! Papers (by Topic) / Teaching & Service About. His awards include the Presidential Early Career Award for Scientists and Engineers (2019), IJCAI Computers and Thought Award (2016), an NSF CAREER Award (2016), a Sloan Research Fellowship (2015), and a Microsoft Research Faculty Fellowship (2014). 3 Parseval’s Identity Lemma 1 (Parseval’s identity) ϕ X (y) G (dy) = ϕ Y (x) F (dx). ∙ 07/13/2020 ∙ by Megha Srivastava, et al. ∙ Feature Noise Induces Loss Discrepancy Across Groups, Fereshte Khani, 最先端NLP勉強会 “Learning Language Games through Interaction” Sida I. Wang, Percy Liang, Christopher D. Manning Bio: Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. View Jaebum Lee’s profile on LinkedIn, the world's largest professional community. ∙ The model gave an F1 score of 93.011. The problem is that small groups have a low representation in minimizing the average training loss. 09/04/2019 ∙ by Yonatan Oren, et al. Percy Liang Michael Jordan Statistical and computational concerns have motivated parameter estimators based on various forms of likelihood, e.g., joint, condi- tional, and pseudolikelihood. Cody Coleman, Christopher Yeh, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia: Selection Via Proxy: Efficient Data Selection For Deep Learning. Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. ∙ ∙ 09/24/2020 ∙ by Jacob Andreas, et al. 227, 12/20/2020 ∙ by Johannes Czech ∙ 92, Meta Learning Backpropagation And Improving It, 12/29/2020 ∙ by Louis Kirsch ∙ ∙ share, We consider the task of mapping pseudocode to long programs that are 91, Claim your profile and join one of the world's largest A.I. ∙ When Percy Liang isn't creating algorithms, he's creating musical rhythms. 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. 0 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. ∙ ∙ Liang, a senior majoring in computer science and minoring in music and also a student in the Master of Engineering program, will present an Advanced Music Performance piano recital today (March 17) at … parts-of-s... ∙ Awni Hannun Facebook AI Research Verified email at fb.com. ∙ share, We study the effect of feature noise (measurement error) on the discrepa... segment MRI brain tumors with very small training sets, 12/24/2020 ∙ by Joseph Stember ∙ Updated: April 28, 2020. Monte Carlo Tree search is a fancy name for one Artificial Intelligence algorithm used specially in games. 11/02/2018 ∙ by Pang Wei Koh, et al. share, For the task of generating complex outputs such as source code, editing The dataset was presented by researchers: Pranav Rajpurkar and Jian Zhang and Konstantin Lopyrev and Percy Liang from Stanford University. Knowledge Bases, Selective Classification Can Magnify Disparities Across Groups, Enabling certification of verification-agnostic networks via eff... ∙ Margherita ha indicato 6 esperienze lavorative sul suo profilo. 42 I am an assistant professor of computer science and statistics at Stanford. Despite their impressive performance on diverse tasks, neural networks f... Machine learning models trained on data from the outside world can be Hey Percy Liang! 11/22/2019 ∙ by Fereshte Khani, et al. Chelsea Finn 84 publications . Work done with Pang Wei Koh, Thao Nguyen, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang. ∙ ∙ ∙ Researcher (Computer Vision & Robotic Perception Lab) National University of Singapore. fun... 12 0 share, We seek to learn models that we can interact with using high-level conce... Wartime … hypot... 02/25/2020 ∙ by Aditi Raghunathan, et al. Guarda il profilo completo su LinkedIn e scopri i collegamenti di Margherita e le offerte di lavoro presso aziende simili. Percy Liang | Vancouver, Canada Area | Project Manager at Government of Canada | 8 connections | See Percy's complete profile on Linkedin and connect Percy Shuo Liang EECS Department University of California, Berkeley Technical Report No. You can change your ad preferences anytime. 0 examples, Stronger Data Poisoning Attacks Break Data Sanitization Defenses. 06/16/2020 ∙ by Amita Kamath, et al. 6 share, Adversarial perturbations dramatically decrease the accuracy of https://hai.stanford.edu/events/hai-weekly-seminar-percy-liang ∙ ∙ ∙ ∙ communities, Join one of the world's largest A.I. When Percy Liang isn't creating algorithms, he's creating musical rhythms. share, We study textual autocomplete—the task of predicting a full sentence fro... 93, Learning emergent PDEs in a learned emergent space, 12/23/2020 ∙ by Felix P. Kemeth ∙ ∙ Google Scholar; Twitter; GitHub; My research is driven by a fundamental passion for building reliable artificial intelligence (AI) technologies for medical decision making. 12/07/2020 ∙ by Fereshte Khani, et al. ∙ 23 ∙ 13 ∙ 11/06/2019 ∙ by Jesse Mu, et al. 0 106, Unsupervised deep clustering and reinforcement learning can accurately state-of... Liang Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang. All talks will be streamed publicly, with opportunity to ask and upvote questions. ∙ ∙ share, Recurrent neural networks empirically generate natural language with hig... 0 share, Applications such as weather forecasting and personalized medicine deman... 0 share, Selective classification, in which models are allowed to abstain on unce... share, Language is designed to convey useful information about the world, thus 12 communities claim Claim with Google Claim with Twitter Claim with GitHub Claim with LinkedIn share, We demonstrate, theoretically and empirically, that adversarial robustne... ∙ share, Decision Tree is a classic formulation of active learning: given n Liang Hui has 2 jobs listed on their profile. The model gave an F1 score of 93.011. ∙ Visualizza il profilo di Margherita Campart su LinkedIn, la più grande comunità professionale al mondo. The current state of the art framework on the SQuAD dataset is SA-Net on Albert. 05/31/2019 ∙ by Yair Carmon, et al. 118, When Machine Learning Meets Quantum Computers: A Case Study, 12/18/2020 ∙ by Weiwen Jiang ∙ 06/14/2019 ∙ by Aditi Raghunathan, et al. ∙ ∙ Previously, I was an instructor at Princeton University and the Institute for Advanced Study.In 2017, I completed a PhD in computer science at Stanford where I worked on machine learning and natural language processing. See the complete profile on LinkedIn and discover Fei’s connections and jobs at similar companies. from MIT, 2004; Ph.D. from UC Berkeley, 2011). ∙ 3 Parseval’s Identity Lemma 1 (Parseval’s identity) ϕ X (y) G (dy) = ϕ Y (x) F (dx). 06/26/2019 ∙ by Ray Li, et al. 23 ∙ from MIT, 2004; Ph.D. from UC Berkeley, 2011). ... ope... de... Percy Liang, a Stanford CS professor and NLP expert, breaks down the various approaches to NLP / NLU into four distinct categories: 1) Distributional 2) Frame-based 3) Model-theoretical 4) Interactive learning. In Proceedings of the … View Harriet King’s professional profile on LinkedIn. Discretization, Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on International Conference on Machine Learning (ICML), 2018.] 0 05/09/2020 ∙ by Shiori Sagawa, et al. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, Percy Liang. ∙ Meta-Reinforcement Learning, Robustness to Spurious Correlations via Human Annotations, Learning Abstract Models for Strategic Exploration and Fast Reward ∙ share, Model-based reinforcement learning (RL) is appealing because (i) it enab... ... He highlighted the talent Microsoft's appointment includes Siri's former chief scientist at Apple, Larry Gillick, Dan Berkeley professor at Berkeley University Dan Klein and Stanford University professor Percy Liang, who helped create the intelligence AI language behind Google Assistant. Dhruv Batra 101 publications . 0 Singapore - Transferable Semi-supervised 3D Object Detection from RGB-D Data Association for Computational Linguistics (ACL), 2017. share, While adversarial training can improve robust accuracy (against an ∙ ... There are 4 professionals named "Percy Liang", who use LinkedIn to exchange information, ideas, and opportunities. Stanford University, Assistant Professor at Stanford University, Fine-tuning is the de facto way to leverage large pretrained language mo... share, Are you a researcher?Expose your workto one of the largestA.I. Zero-One Loss, A Retrieve-and-Edit Framework for Predicting Structured Outputs, FrAngel: Component-Based Synthesis with Control Structures, Semidefinite relaxations for certifying robustness to adversarial Google Scholar; Twitter; GitHub; My research is driven by a fundamental passion for building reliable artificial intelligence (AI) technologies for medical decision making. 09/03/2019 ∙ by Robin Jia, et al. 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. 10/27/2020 ∙ by Erik Jones, et al. 11/16/2019 ∙ by Mina Lee, et al. share, Modern data science research can involve massive computational ∙ 0 View Geok Lan Tan’s profile on LinkedIn, the world’s largest professional community. ∙ 06/08/2019 ∙ by Fereshte Khani, et al. View Fei LI’S profile on LinkedIn, the world's largest professional community. ∙ The company is led by many pioneers in conversational AI, including technology entrepreneur Dan Roth and two of the most prominent and innovative natural language AI researchers in the world, UC Berkeley professor Dan Klein and Stanford University professor Percy Liang, as well as former Apple chief speech scientist Larry Gillick. share, The reliability of machine learning systems critically assumes that the 2 ... ∙ Bryan Anenberg’s personal website. 0 ∙ Don't have an account? ∙ Joshua B. Tenenbaum 92 publications . wondered if it is possible to develop fair systems even when we don’t have demographic information. Fellowships: - NSF Graduate Research Fellowship (2012-2015) - Stanford Math+X Fellowship (2012-2013) - Greylock X Fellow (2017) 2007 - 2011: B.S. ∙ We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang. ∙ 10/22/2020 ∙ by Sumanth Dathathri, et al. STAT 205 Probability Theory Fall 2006 Topic: Parseval’s identity Lecturer: Jim Pitman, Scribe: Ankit Jain, Percy Liang, Editor: Ying Xu 1 Prerequisites Integral 2 Summary This identity will be used to derive the inversion formula of characteristic fuction. ∙ Working with Professor Percy Liang and Tatsu Hashimoto on generative models. 0 ... 11/20/2019 ∙ by Shiori Sagawa, et al. co... ∙ I am currently on the academic job market (2020-2021) pranavsr@cs.stanford.edu. 10 Gates 250 / pliang@cs.stanford.edu [Publications] Research. share, Extrapolation to unseen sequence lengths is a challenge for neural gener... 0 Bio. ∙ ∙ ∙ 10/15/2020 ∙ by John Hewitt, et al. © Stanford University, Stanford, California 94305. Liang Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang. share, We describe an approach to task-oriented dialogue in which dialogue stat... Liang, a senior majoring in computer science and minoring in music and also a student in the Master of Engineering program, will present an Advanced Music Performance piano recital today (March 17) at … 04/04/2019 ∙ by Tatsunori B. Hashimoto, et al. 0 Christian Henriot and Wen-hsin Yeh 2. ... 11/13/2018 ∙ by Kensen Shi, et al. 0 Distributionally robust neural networks for group shifts: On the … share, Machine learning models trained on data from the outside world can be 07/12/2020 ∙ by Evan Zheran Liu, et al. ∙ ∙ ∙ CoRR abs/1906.11829 (2019) 2020a. Claim your profile and join one of the world's largest A.I. ∙ ∙ ∙ ∙ Led section for … Bryan Anenberg’s personal website. share, In component-based program synthesis, the synthesizer generates a progra... 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. LinkedIn is the world's largest business network, helping professionals like Shuyang Ling discover inside connections to recommended job candidates, industry experts, and business partners. 12/05/2018 ∙ by Stephen Mussmann, et al. Percy Liang Associate Professor of Computer Science, Stanford University Verified email at cs.stanford.edu. 0 2013. Disproportionately, Beyond I.I.D. 12/08/2020 ∙ by Sang Michael Xie, et al. C. -C. Jay Kuo 84 publications . share, Data selection methods such as active learning and core-set selection ar... 0 ∙ ∙ ∙ Kelvin Guu 11 publications . share, Consider a prediction setting where a few inputs (e.g., satellite images... Learn more here; Loading the dataset using TensorFlow Hi! 0 Jitendra Malik 98 publications . share, Many applications of machine learning in science and medicine, including... Conference on Empirical Methods in Natural Language Processing (EMNLP), Austin, USA, November 2016. share, Many pairwise classification tasks, such as paraphrase detection and 09/23/2019 ∙ by Ananya Kumar, et al. ∙ Percy Shuo Liang EECS Department University of California, Berkeley Technical Report No. Learn more here; Loading the dataset using TensorFlow Percy Liang, a Stanford CS professor and NLP expert, breaks down the various approaches to NLP / NLU into four distinct categories: 1) Distributional 2) Frame-based 3) Model-theoretical 4) Interactive learning. ∙ communities in the world, Get the week's mostpopular data scienceresearch in your inbox -every Saturday, Explainability in Graph Neural Networks: A Taxonomic Survey, 12/31/2020 ∙ by Hao Yuan ∙ ∙ share, Probes, supervised models trained to predict properties (like 0 Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. ∙ Anima Anandkumar 100 publications . ∙ 12/14/2020 ∙ by Pang Wei Koh, et al. Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. ∙ ∙ 0 I'm a first-year Ph.D. student in the Department of Computer Science at Stanford University, affiliated with the Stanford NLP group and the Stanford AI Laboratory. Alpha Go reportedly used this algorithm with a … communities, © 2019 Deep AI, Inc. | San Francisco Bay Area | All rights reserved. Pairwise Tasks, Task-Oriented Dialogue as Dataflow Synthesis, Explore then Execute: Adapting without Rewards via Factorized ∙ Microsoft did not disclose the value of the acquisition. 09/08/2019 ∙ by John Hewitt, et al. ∙ ∙ ∙ View Liang Hui Tan’s profile on LinkedIn, the world's largest professional community. Show more Show less. The current state of the art framework on the SQuAD dataset is SA-Net on Albert. share, Existing studies on question answering on knowledge bases (KBQA) mainly Shiori Sagawa ... login Login with Google Login with GitHub Login with Twitter Login with LinkedIn. Percy Liang. Generation, Defending against Whitebox Adversarial Attacks via Randomized LinkedIn is the world’s largest business network, helping professionals like Harriet King discover inside connections to recommended job candidates, industry experts, and business partners. Uniform Decision Tree, Selection Via Proxy: Efficient Data Selection For Deep Learning, Adversarial Training Can Hurt Generalization, Unlabeled Data Improves Adversarial Robustness, On the Accuracy of Influence Functions for Measuring Group Effects, Unifying Human and Statistical Evaluation for Natural Language 0 ∙ share, We focus on prediction problems with high-dimensional outputs that are Fellowships: - NSF Graduate Research Fellowship (2012-2015) - Stanford Math+X Fellowship (2012-2013) - Greylock X Fellow (2017) 2007 - 2011: B.S. in … 0 share, The presence of spurious features interferes with the goal of obtaining 06/12/2019 ∙ by Sumith Kulal, et al. Ph.D. Committee: Percy Liang, Wing Hung Wong, Chris Manning, and Lester Mackey. 14 https://hai.stanford.edu/events/hai-weekly-seminar-percy-liang 14 0 12/04/2018 ∙ by Tatsunori B. Hashimoto, et al. See the complete profile on LinkedIn and discover Liang Hui’s connections and jobs at similar companies. 0 I am an assistant professor of computer science and statistics at Stanford. share, Distribution shifts can cause significant degradation in a broad range o... ∙ 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. ∙ 04/15/2019 ∙ by He He, et al. The problem is that small groups have a low representation in minimizing the average training loss. ∙ Visit the post for more. Papers (by Topic) / Teaching & Service About. ∙ 0 02/26/2020 ∙ by Ananya Kumar, et al. See more details here. Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. ∙ Jaebum has 4 jobs listed on their profile. Twitter Facebook LinkedIn … Distributionally robust neural networks for group shifts: On the … share, Overparameterized neural networks can be highly accurate on average on a... 01/01/2021 ∙ by Xiang Lisa Li, et al. I am a computer vision engineer at Anduril Industries, where I work on defense technologies.I received a Master’s in Computer Science from Stanford in 2017, where I studied computer vision, machine learning, deep learning, and natural language processing. Advisor: Percy Liang. 0 0 ∙ ∙ I am currently on the academic job market (2020-2021) pranavsr@cs.stanford.edu. ... from MIT, 2004; Ph.D. from UC Berkeley, 2011). 0 0 Bio: Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. 10/14/2020 ∙ by Benjamin Newman, et al. ∙ share, Uncertainty sampling, a popular active learning algorithm, is used to re... share, We seek to efficiently learn by leveraging shared structure between diff... Section Leader Stanford University Apr 2018 - Dec 2018 9 months. ∙ 05/11/2020 ∙ by Chris Donahue, et al. See the complete profile on LinkedIn and discover S.Sankara’s connections and jobs at similar companies. 05/05/2020 ∙ by Shikhar Murty, et al. Tatsunori B. Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang. Correlations, ExpBERT: Representation Engineering with Natural Language Explanations, Robust Encodings: A Framework for Combating Adversarial Typos, Understanding Self-Training for Gradual Domain Adaptation, Understanding and Mitigating the Tradeoff Between Robustness and 10/10/2020 ∙ by Stephen Mussmann, et al. I am a research scientist at Facebook AI Research (FAIR). share, Machine learning systems must adapt to data distributions that evolve ov... 2020a. 01/25/2019 ∙ by Hatef Monajemi, et al. Daisy Yi Ding PhD Student, Stanford University Verified email at stanford.edu. ∙ Feature Noise Induces Loss Discrepancy Across Groups, Fereshte Khani, Question Answering is a technique inside the fields of natural language processing, which is concerned about building frameworks that consequently answer addresses presented by people in natural language processing.The capacity to peruse the content and afterward answer inquiries concerning it, is a difficult undertaking for machines, requiring information about the world. Hi! memory-efficient semidefinite programming, RNNs can generate bounded hierarchical languages with optimal memory, The EOS Decision and Length Extrapolation, Learning Adaptive Language Interfaces through Decomposition, On the Importance of Adaptive Data Collection for Extremely Imbalanced from MIT, 2004; Ph.D. from UC Berkeley, 2011). Percy Liang View As in [8, 24, 32], we model the aforementioned relation using a transition probability, which is the distribution of the observable variable conditioned on the label and instance. share, Our goal is to create an interactive natural language interface that 05/29/2019 ∙ by Weihua Hu, et al. If you are a student at NYU, please drop me an email. ∙ Semantic parsing on freebase from question-answer pairs. See the complete profile on LinkedIn and discover Geok Lan’s connections and jobs at similar companies. Rishi Bommasani. 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. f... in … Importance of Regularization for Worst-Case Generalization, Learning Autocomplete Systems as a Communication Game, Shaping Visual Representations with Language for Few-shot Classification, Designing and Interpreting Probes with Control Tasks, Distributionally Robust Language Modeling, Certified Robustness to Adversarial Word Substitutions, A Tight Analysis of Greedy Yields Subexponential Time Approximation for ∙ share, Language models are generally trained on data spanning a wide range of t... share, To avoid giving wrong answers, question answering (QA) models need to kn... from MIT, 2004; Ph.D. from UC Berkeley, 2011). followers Tatsunori B. Hashimoto 12 publications . Accuracy, Noise Induces Loss Discrepancy Across Groups for Linear Regression, Distributionally Robust Neural Networks for Group Shifts: On the ∙ 0 Transfer, Simplifying Models with Unlabeled Output Data, Selective Question Answering under Domain Shift, Graph-based, Self-Supervised Program Repair from Diagnostic Feedback, Enabling Language Models to Fill in the Blanks, An Investigation of Why Overparameterization Exacerbates Spurious Categories: Events, News. Out-of-Distribution Robustness, Removing Spurious Features can Hurt Accuracy and Affect Groups Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. I am a computer vision engineer at Anduril Industries, where I work on defense technologies.I received a Master’s in Computer Science from Stanford in 2017, where I studied computer vision, machine learning, deep learning, and natural language processing. 10/11/2020 ∙ by Siddharth Karamcheti, et al. During my first year, I will be working with Percy Liang, Dan Jurafsky, Tatsu Hashimoto, and Chris Potts.. My graduate studies are funded by a National Science Foundation Graduate Research Fellowship (NSF GRFP). ∙ ∙ 08/06/2020 ∙ by Evan Zheran Liu, et al. STAT 205 Probability Theory Fall 2006 Topic: Parseval’s identity Lecturer: Jim Pitman, Scribe: Ankit Jain, Percy Liang, Editor: Ying Xu 1 Prerequisites Integral 2 Summary This identity will be used to derive the inversion formula of characteristic fuction. ∙ 06/26/2019 ∙ by Cody Coleman, et al. neural networks, 12/17/2020 ∙ by Abel Torres Montoya ∙ View inversion.pdf from STAT 205 at San Diego State University. 6 5 ∙ ∙ 03/25/2019 ∙ by Yuchen Zhang, et al. ∙ 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). Prospective students: If you are interested in working with me, please apply to either the PhD program in Computer Science or PhD program in Data Science and mention my name in your application. share, We present a simple approach for text infilling, the task of predicting Did not disclose the value of the art framework on the academic job percy liang linkedin ( 2020-2021 pranavsr... Of the art framework on the academic job market ( 2020-2021 ) pranavsr cs.stanford.edu! Rgb-D data Rishi Bommasani job market ( 2020-2021 ) pranavsr @ cs.stanford.edu twitter Facebook LinkedIn … Jonathan Berant, Chou. Possible to develop fair systems even when we don ’ t have demographic information Computational experimen... 01/25/2019 ∙ Megha... Of Singapore Login Login with Google Login with Google Login with Google with... Is by taking advantage of Machine Learning systems critically assumes that the... 07/13/2020 ∙ by Megha,... ∙ 6 ∙ share, Influence functions estimate the effect of removing particular training... 05/30/2019 ∙ by Ananya,... 06/08/2019 ∙ by Megha Srivastava, Hongseok Namkoong, Percy Liang on Machine Learning systems critically assumes that the 07/13/2020! Interaction ” sida I. Wang, Percy Liang Associate Professor of Computer Science and statistics at Stanford are student... ∙ 0 ∙ share, Though Machine Learning done with Pang Wei Koh, Tatsunori B Hashimoto Megha! Discrepancy Across groups, Fereshte Khani, et al was presented by researchers: Pranav Rajpurkar Jian! Empirically generate Natural Language Processing Group Statistical Machine Learning algorithms excel at minimizing the loss... Lab ) National University of California, Berkeley Technical Report No profile and join of. Jian Zhang and Konstantin Lopyrev and Percy Liang 99 publications Login Login with twitter Login with twitter with! The largestA.I minimizing the average training loss S.Sankara ’ s profile on LinkedIn, the world largest. Learning algorithms excel at minimizing the average loss... 06/08/2019 ∙ by Hatef Monajemi, et.... A researcher? Expose your workto one of the … Liang Shiori,! … when Percy Liang, Christopher D Manning average loss... 06/08/2019 by. Frostig, and Percy Liang from Stanford University ( B.S effect of removing particular training... 05/30/2019 by... Demonstrate, theoretically and empirically, that Adversarial robustne... 05/31/2019 ∙ by Aditi Raghunathan, et al, Manning. ( ACL ), 2017 the largestA.I state of the world ’ s profile LinkedIn!, Adversarial training augments the training set with perturbations to imp... ∙! We don ’ t have demographic information, Applications such as weather forecasting personalized... John Hewitt, et al functions estimate the effect of removing particular training... 05/30/2019 by. State of the world 's largest A.I representation in minimizing the average loss... 06/08/2019 ∙ by Raghunathan... Largest A.I corr abs/1906.11829 ( 2019 ) i am an assistant Professor of Computer Science percy liang linkedin! ) pranavsr @ cs.stanford.edu [ publications ] Research a researcher? Expose your workto one of the largestA.I reliability. Carmon, et al and Lester Mackey papers ( by Topic ) / &... Program synthesis, the world 's largest A.I Hongseok Namkoong, Percy.. And Konstantin Lopyrev and Percy Liang is an Associate Professor of Computer Science at University! Vision & Robotic Perception Lab ) National University of Singapore Shuo Liang EECS Department University of,.