PPT-Learning for Structured Prediction

Overview of the Material TexPoint fonts used in EMF Read the TexPoint manual before you delete this box A A A A A A A A A A A A A A A A A Outline 2 Type of structures considered. edu Dan Roth danrillinoisedu Abstract Structured prediction is the cornerstone of several machine learning applications Un fortunately in structured prediction settings with expressive intervariable interactions exact inferencebased learning algorith Nam Vo & Aaron . Bobick. ICRA 2015. Structured Activity. Long sequence composed of multiple actions with a temporal structure (defined by a grammar).. Sequential Interval Network (. SIN):. recognize the sequence of actions. Peter Dayan. Gatsby Computational Neuroscience Unit. Neural Decision Making. bewilderingly vast topic . models playing a central role. so beware of self-confirmation + battles. 3. Ethology/Economics(?). Reinforcement learning I: . prediction . classical conditioning . dopamine. Reinforcement learning II:. dynamic programming; action selection. Pavlovian. . misbehaviour. vigor. Chapter 9 of Theoretical Neuroscience. Sanjeev. . Arora. , . Rong. . Ge. Princeton University. Learning Parities with Noise. Secret u = (1,0,1,1,1). u ∙ (0,1,0,1,1) = 0. u ∙ (1,1,1,0,1) = 1. u ∙ (0,1,1,1,0) = . 1. Learning Parities with Noise. Prediction is important for action selection. The problem:. prediction of future reward. The algorithm:. temporal difference learning. Neural implementation:. dopamine dependent learning in BG. A precise computational model of learning allows one to look in the brain for “hidden variables” postulated by the model. Introductions . Name. Department/Program. If research, what are you working on.. Your favorite fruit.. How do you estimate P(. y|x. ) . Types of Learning. Supervised Learning. Unsupervised Learning. Semi-supervised Learning. Outline. Some Sample NLP Task . [Noah Smith]. Structured Prediction For NLP. Structured Prediction Methods. Conditional Random Fields. Structured . Perceptron. Discussion. Motivating Structured-Output Prediction for NLP. Steve Branson . Oscar . Beijbom. . Serge . Belongie. CVPR 2013, Portland, Oregon. . UC San Diego. . UC San Diego. . Caltech. Overview. Structured prediction . Learning from larger datasets. Prediction is important for action selection. The problem:. prediction of future reward. The algorithm:. temporal difference learning. Neural implementation:. dopamine dependent learning in BG. A precise computational model of learning allows one to look in the brain for “hidden variables” postulated by the model. Reinforcement learning I: . prediction . classical conditioning . dopamine. Reinforcement learning II:. dynamic programming; action selection. Pavlovian. . misbehaviour. vigor. Chapter 9 of Theoretical Neuroscience. Steve Branson . Oscar . Beijbom. . Serge . Belongie. CVPR 2013, Portland, Oregon. . UC San Diego. . UC San Diego. . Caltech. Overview. Structured prediction . Learning from larger datasets. Sanjeev. . Arora. , . Rong. . Ge. Princeton University. Learning Parities with Noise. Secret u = (1,0,1,1,1). u ∙ (0,1,0,1,1) = 0. u ∙ (1,1,1,0,1) = 1. u ∙ (0,1,1,1,0) = . 1. Learning Parities with Noise. prediction . classical conditioning . dopamine. Reinforcement learning II:. dynamic programming; action selection. Pavlovian. . misbehaviour. vigor. Chapter 9 of Theoretical Neuroscience. (thanks to Yael .