Computer Vision Group Prof. Daniel Cremers. 16. Online Learning
|
|
- Candice Holmes
- 5 years ago
- Views:
Transcription
1 Prof. Daniel Cremers 16.
2 Motivation So far, we have handled offline learning methods, but very often data is observed in an ongoing process Therefore, it would be good to adapt the learned models with newly arriving data without having to consider old data This is called online learning Major benefits: algorithms are adaptive to new observations learning is usually faster 2
3 Clarification of Notions There are (at least) three notions: incremental learning: model is updated with new samples, but old samples might be considered again online learning: after considering a data sample, it can be disregarded (no need to store it) learning at frame rate: learning is fast enough such that it can be performed in one perception cycle 3
4 Example: Pedestrian Detection Offline Approach: 1. Collect and annotate a large data set from different sensor modalities, here: camera and 2D laser Training Set Training Set Codebook Laser Data Image Data 4 [Spinello, Triebel, and Siegwart, IJRR 21]
5 Example: Pedestrian Detection Offline Approach: 1. Collect and annotate a large data set from different sensor modalities, here: camera and 2D laser 2. Train a classifier for each sensor modality Training Set Training Set Boosted CRF Extended ISM Codebook Laser Data Image Data 5 [Spinello, Triebel, and Siegwart, IJRR 21]
6 Example: Pedestrian Detection Offline Approach: 1. Collect and annotate a large data set from different sensor modalities, here: camera and 2D laser 2. Train a classifier for each sensor modality 3. Apply the classifiers and fuse data Training Set Training Set Boosted CRF Extended ISM Codebook Laser Data New Laser Data Stream Image Data New Image Data Stream 6 [Spinello, Triebel, and Siegwart, IJRR 21]
7 Example: Pedestrian Detection Testing Phase: Fused pedestrian detection and tracking Fused detection and tracking of cars and pedestrians But: non-adaptive; large training set required [Spinello, Triebel, and Siegwart, IJRR 21] 7
8 Major Problem of this Approach Offline learning: cannot adapt to new environments cannot learn new classes cannot consider new instances of a given class is often very slow requires a large amount of manually annotated training data Ideas: use online learning for adaptivity use active learning to reduce (human) work load 8
9 Active Learning To reduce the required training data, the learner can select the data it needs to learn from. This is called active learning Major advantages: only those samples where classification is hard are used for re-training humans only need to give ground truth labels for a smaller set of samples In principle, active learning can be used with offline and online learning, but online makes more sense 9
10 Active Learning Training data Optimization function f(x) training data Laptop Y Cup f(x) X 1
11 Active Learning Training data New Data Optimization function f(x) Prediction Uncertainty, Labels training data Laptop Y Cup f(x) f(x) X Laptop 11
12 Active Learning Training data New Data Optimization function f(x) Prediction Uncertainty, Labels training data Laptop Y Cup f(x) f(x) X? 12
13 Active Learning Training data New Data Supervisor Optimization function f(x) Prediction Uncertainty, Labels Label Query training data Laptop Y Cup f(x) X Present 13
14 Active Learning Training data New Data Supervisor Optimization function f(x) Prediction Uncertainty, Labels Label Query New training data Extend training data training data Laptop Y Cup f(x) X Present 14
15 Active Learning Training data New Data Supervisor Optimization function f(x) Prediction Uncertainty, Labels Label Query New training data Extend training data Major Benefits: Adapts to new situations Requires less training samples 15
16 Uncertainty Estimates A key step in active learning is the selection step It requires a good estimate of uncertainties Examples for classification algorithms to compute uncertainties: Support Vector Machine ( Platt scaling ) Gaussian Process Classifier ( predictive variance ) Tree-based classifiers (entropy in leaf nodes) But: It is important how uncertainty correlates to incorrect classifications! 16
17 Uncertainty Estimation: An Example building tree ground hedge car background 1 Ground Truth GP Classification Comparison by evaluation on an unseen class: SVM Classifier GP Classifier 3 2 Uncertainty Frequency SVM Frequency GPC The GP is less overconfident than the SVM! Normalized Entropy for Label Distribution uncertainty Normalized Entropy for Label Distribution uncertainty 17 [Paul, Triebel, Rus, Newman, IROS 212]
18 Trained classes Unseen classes Application: Traffic Sign Classification Lorry Stop Roadworks Keep left 7kph Right ahead IVM uncertainty histograms IVM Non-linear GPC IVM Non-linear 8 6 Non-linear Linear GPC 4 GPC GPC 2 Linear Non-linear GPC Linear SVM GPC Non-linear Non-linear Linear SVM SVM SVM Linear Logit SVM Linear Boost SVM Logit Boost Logit BDT Boost Trained classes Lorry Stop Roadworks 1 Keep left Trained classes 2 Lorry 5 4 Stop Roadworks Keep left Unseen classes Unseen classes kph kph Right 25 ahead Right ahead PD 4 Dr. 5 Rudolph Triebel 1 5 Computer.5 Vision 1 Group 2 5 Right ahead The GP is less overconfident than the SVM! [Grimmett, Paul, Triebel, Posner ICRA 213]
19 Over- and Underconfidence Definition 1: The overconfidence of a classifier is the mean of all confidence values that correspond to incorrect classifications. Definition 2: The underconfidence of a classifier is the mean of all uncertainty values that correspond to correct classifications. 19
20 The 3 Criteria of Learning Algorithms Efficiency Accuracy memory run time precision recall P R: Tracking and fusion PED class Camera Laser Fusion Run time recall Recall Memory Precision precision
21 The 3 Criteria of Learning Algorithms Efficiency Accuracy memory run time precision recall Confidence overconfidence underconfidence 21
22 Active Learning for Semantic Mapping Active Learning is well suited for semantic mapping because: it can deal with large amounts of data. data is not independent. the task is essentially an online learning problem. 22 PD Dr. Rudolph Triebel
23 Active Learning for Semantic Mapping Training data New Batch Data Supervisor function Train Optimization IVM hyperparams f(x) active set Predict and Prediction Sort Uncertainty, Labels query most Label uncertain Query New training data Extend and training forget training data data Concrete Approach: Use IVM (a sparse online GP) for Template 1 5 Image Window classification Sort classified data by uncertainty Request labels for the most uncertain samples = 2 = =. 3 2 n 1 3 n 2 n n N Remove uninformative samples ( forgetting ) 23 [Triebel, Grimmett, Paul, Posner ISRR 213]
24 The Informative Vector Machine Main differences to standard GP classifier: it uses a subset ( active set ) of training points the (inverse) posterior covariance matrix is computed incrementally Decision of inclusion in the active set based on infor- mation-theoretic criterion Slight caveat: Training of hyper-parameters needs to be done iteratively From: 24
25 Semantic Mapping: Results false positives true positions high number of detections low Passive&detector& Ac3ve&detector& Epoch&& Epoch&2& Epoch&9& GP overtakes and stays better than SVM. Active learning better than passive learning. performance f 1 measure Random selection is not better. 25 SVM active SVM passive SVM random IVM active IVM passive IVM random Epoch no. epoch [Triebel, Grimmett, Paul, Posner ISRR 213]
26 Which Classifier Should We Choose? high Boosting Efficiency SVM GPC low low Accuracy high 26 PD Dr. habil. Rudolph Triebel
27 Which Classifier Should We Choose? high Boosting Efficiency low Conf. Est. bad good GPC SVM low Accuracy high SVMs are accurate, but (more) overconfident GPCs are less overconfident, but very inefficient Boosting is very efficient, but also overconfident 27 PD Dr. habil. Rudolph Triebel
28 Can We Reduce Over-(Under-)Confidence? Start with a very efficient multi-class boosting classifier Modify it so that it reduces overconfidence Use also the confidence to weight training samples Result ( Confidence Boosting ): wrong, certain classified samples receive higher weight overconfidence reduced in every learning round overall classifier is less overconfident better for Active Learning Note: This is the alternative approach to making a non-overconfident classifier efficient! 28 PD Dr. habil. Rudolph Triebel
29 Online Gradient Boosting Online: outer loop over data points, inner loop over weak classifiers For each point, all weak classifiers are updated Algorithm 1: Online Multi-class Gradient Boost [Sa ari et al. 21] Data: training data (X, y) withc classes Input: number of weak learners M, loss function `, agreement function a Output: weak learners f 1,...,f M 1 Initialize(f 1,...,f M ) 2 for n =1,...,N do 3 w n 1 4 g n 5 for m =1,...,M do 6 f m UpdateWeakLearner(f m, x n,y n,w n ) 7 p nm f m (x n ) 8 nm a(p nm,y n ) 9 g n g n + nm 1 w n r`(g n ) 11 end 12 end Agreement between prediction and ground truth Sample receives low weight if agreement high Note: Agreement does not use the confidence! 29
30 Confidence Boosting Main idea: Use also the confidence to compute the agreement Intuitively: if classification is correct use the positive confidence if classification is wrong use negative confidence Result: wrong, certain classified samples receive higher weight overconfidence reduced in every learning round overall classifier is less overconfident better for Active Learning 3
31 Example: AL for 3D Object Recognition Qualitative Results: True Label = binder True Label = lime kleenex lemon lightbulb lime marker apple ball banana ballpepper binder Epoch 1 True Label = bowl Gradient Boost >calculator Confidence Boost >binder bowl calculator camera cap cellphone cerealbox coffeemug.25.2 Epoch 1 Gradient Boost >lemon Confidence Boost >lime kleenex lemon lightbulb lime marker apple ball banana ballpepper binder bowl calculator camera 31 cap cellphone cerealbox coffeemug Epoch 1 kleenex lemon lightbulb lime marker apple ball banana ballpepper binder bowl Gradient Boost >coffeemug Confidence Boost >bowl calculator camera cap cellphone cerealbox coffeemug
32 Example: AL for 3D Object Recognition Avg. Classification Error Saffari et al. act. GradientBoost act. Confidence Boosting Lai et al. no. queries Pendigits GB Pendigits CB USPS GB USPS CB Letter GB Letter CB USPS Letter Pendigits DNA Begbroke RGBD epochs Confidence Boosting classifies better than GradientBoost. generates fewer label queries. is less overconfident. is orders of magnitude faster than GPC. 32 GB CB correct false
33 Pool-based and Stream-based AL Problem: Most often, data occurs in streams (online) and not in pools (offline) But: Online Random Forests require a balanced class dist. depend on the order of the data Idea: use Mondrian Forests [1] Main differences: data stream MFs also store the range of the data in each dimension MFs are independent on the class labels [1] B. Lakshminarayanan, D. M. Roy, and Y. W. Teh, Mondrian Forests: Efficient Online Random Forests, in Advances in Neural Information Processing Systems (NIPS), 214, pp PD Dr. habil. Rudolph Triebel
34 Mondrian Forests start with two points insert a split 34 PD Dr. habil. Rudolph Triebel
35 Mondrian Forests start with two points insert a split add a third point 35 PD Dr. habil. Rudolph Triebel
36 Mondrian Forests start with two points insert a split add a third point sample a time from an exponential distr. insert a node above the given node insert a random split 36 PD Dr. habil. Rudolph Triebel
37 Mondrian Forests start with two points insert a split add a third point sample a time from an exponential distr. insert a node above the given node insert a random split add a new node inside the outer box 37 PD Dr. habil. Rudolph Triebel
38 Mondrian Forests start with two points insert a split add a third point sample a time from an exponential distr. insert a node above the given node insert a random split add a new node inside the outer box sample again and insert new node at the end this requires extending a split 38 PD Dr. habil. Rudolph Triebel
39 Why the Name Mondrian Forests? 39 PD Dr. habil. Rudolph Triebel
40 Why the Name Mondrian Forests? Piet Mondrian: Composition with Red, Yellow, Blue, and Black 1926 Gemeentemuseum, Den Haag 4 PD Dr. habil. Rudolph Triebel
41 Application to Real Data KiTTI benchmark data set: 3D point clouds cars, pedestrians, bikes, trucks, etc. segmentation given ( tracklets ) Goal: online classification use active learning Major problems: un-balanced classes order of appearance 41 PD Dr. habil. Rudolph Triebel
42 The Data Set The real data The data uniformly resampled 42 PD Dr. habil. Rudolph Triebel
43 Results (no Active Learning) The real data The data uniformly resampled A. Narr, R. Triebel, D. Cremers Stream-based Active Learning for Efficient and Adaptive Classification of 3D Objects in: ICRA PD Dr. habil. Rudolph Triebel
44 Results Using Active Learning Mondrian Forests require only 5% of the data to reach 9% accuracy Standard Random Forests can not reach that A. Narr, R. Triebel, D. Cremers Stream-based Active Learning for Efficient and Adaptive Classification of 3D Objects in: ICRA PD Dr. habil. Rudolph Triebel
45 Summary Online learning has important advantages over offline learning: efficiency and adaptivity In active learning the algorithm selects the data to learn from (human in the loop) This requires good confidence estimates The GP classifiers tends to be less overconfident, but inefficient A faster alternative method is Confidence Boosting, it is very efficient and not much overconfident For stream-based Active Learning Mondrian Forests are better suited 45
Lecture 1: Machine Learning Basics
1/69 Lecture 1: Machine Learning Basics Ali Harakeh University of Waterloo WAVE Lab ali.harakeh@uwaterloo.ca May 1, 2017 2/69 Overview 1 Learning Algorithms 2 Capacity, Overfitting, and Underfitting 3
More informationPython Machine Learning
Python Machine Learning Unlock deeper insights into machine learning with this vital guide to cuttingedge predictive analytics Sebastian Raschka [ PUBLISHING 1 open source I community experience distilled
More informationMachine Learning and Data Mining. Ensembles of Learners. Prof. Alexander Ihler
Machine Learning and Data Mining Ensembles of Learners Prof. Alexander Ihler Ensemble methods Why learn one classifier when you can learn many? Ensemble: combine many predictors (Weighted) combina
More informationIntroduction to Ensemble Learning Featuring Successes in the Netflix Prize Competition
Introduction to Ensemble Learning Featuring Successes in the Netflix Prize Competition Todd Holloway Two Lecture Series for B551 November 20 & 27, 2007 Indiana University Outline Introduction Bias and
More informationRule Learning With Negation: Issues Regarding Effectiveness
Rule Learning With Negation: Issues Regarding Effectiveness S. Chua, F. Coenen, G. Malcolm University of Liverpool Department of Computer Science, Ashton Building, Ashton Street, L69 3BX Liverpool, United
More informationModule 12. Machine Learning. Version 2 CSE IIT, Kharagpur
Module 12 Machine Learning 12.1 Instructional Objective The students should understand the concept of learning systems Students should learn about different aspects of a learning system Students should
More informationA Case Study: News Classification Based on Term Frequency
A Case Study: News Classification Based on Term Frequency Petr Kroha Faculty of Computer Science University of Technology 09107 Chemnitz Germany kroha@informatik.tu-chemnitz.de Ricardo Baeza-Yates Center
More informationCS Machine Learning
CS 478 - Machine Learning Projects Data Representation Basic testing and evaluation schemes CS 478 Data and Testing 1 Programming Issues l Program in any platform you want l Realize that you will be doing
More informationQuickStroke: An Incremental On-line Chinese Handwriting Recognition System
QuickStroke: An Incremental On-line Chinese Handwriting Recognition System Nada P. Matić John C. Platt Λ Tony Wang y Synaptics, Inc. 2381 Bering Drive San Jose, CA 95131, USA Abstract This paper presents
More informationSystem Implementation for SemEval-2017 Task 4 Subtask A Based on Interpolated Deep Neural Networks
System Implementation for SemEval-2017 Task 4 Subtask A Based on Interpolated Deep Neural Networks 1 Tzu-Hsuan Yang, 2 Tzu-Hsuan Tseng, and 3 Chia-Ping Chen Department of Computer Science and Engineering
More informationCSL465/603 - Machine Learning
CSL465/603 - Machine Learning Fall 2016 Narayanan C Krishnan ckn@iitrpr.ac.in Introduction CSL465/603 - Machine Learning 1 Administrative Trivia Course Structure 3-0-2 Lecture Timings Monday 9.55-10.45am
More informationUnsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model
Unsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model Xinying Song, Xiaodong He, Jianfeng Gao, Li Deng Microsoft Research, One Microsoft Way, Redmond, WA 98052, U.S.A.
More informationArtificial Neural Networks written examination
1 (8) Institutionen för informationsteknologi Olle Gällmo Universitetsadjunkt Adress: Lägerhyddsvägen 2 Box 337 751 05 Uppsala Artificial Neural Networks written examination Monday, May 15, 2006 9 00-14
More informationRule Learning with Negation: Issues Regarding Effectiveness
Rule Learning with Negation: Issues Regarding Effectiveness Stephanie Chua, Frans Coenen, and Grant Malcolm University of Liverpool Department of Computer Science, Ashton Building, Ashton Street, L69 3BX
More informationActive Learning. Yingyu Liang Computer Sciences 760 Fall
Active Learning Yingyu Liang Computer Sciences 760 Fall 2017 http://pages.cs.wisc.edu/~yliang/cs760/ Some of the slides in these lectures have been adapted/borrowed from materials developed by Mark Craven,
More informationGenerative models and adversarial training
Day 4 Lecture 1 Generative models and adversarial training Kevin McGuinness kevin.mcguinness@dcu.ie Research Fellow Insight Centre for Data Analytics Dublin City University What is a generative model?
More informationarxiv: v1 [cs.lg] 15 Jun 2015
Dual Memory Architectures for Fast Deep Learning of Stream Data via an Online-Incremental-Transfer Strategy arxiv:1506.04477v1 [cs.lg] 15 Jun 2015 Sang-Woo Lee Min-Oh Heo School of Computer Science and
More informationLinking Task: Identifying authors and book titles in verbose queries
Linking Task: Identifying authors and book titles in verbose queries Anaïs Ollagnier, Sébastien Fournier, and Patrice Bellot Aix-Marseille University, CNRS, ENSAM, University of Toulon, LSIS UMR 7296,
More informationMulti-Lingual Text Leveling
Multi-Lingual Text Leveling Salim Roukos, Jerome Quin, and Todd Ward IBM T. J. Watson Research Center, Yorktown Heights, NY 10598 {roukos,jlquinn,tward}@us.ibm.com Abstract. Determining the language proficiency
More informationLEGO MINDSTORMS Education EV3 Coding Activities
LEGO MINDSTORMS Education EV3 Coding Activities s t e e h s k r o W t n e d Stu LEGOeducation.com/MINDSTORMS Contents ACTIVITY 1 Performing a Three Point Turn 3-6 ACTIVITY 2 Written Instructions for a
More information(Sub)Gradient Descent
(Sub)Gradient Descent CMSC 422 MARINE CARPUAT marine@cs.umd.edu Figures credit: Piyush Rai Logistics Midterm is on Thursday 3/24 during class time closed book/internet/etc, one page of notes. will include
More informationExperiments with SMS Translation and Stochastic Gradient Descent in Spanish Text Author Profiling
Experiments with SMS Translation and Stochastic Gradient Descent in Spanish Text Author Profiling Notebook for PAN at CLEF 2013 Andrés Alfonso Caurcel Díaz 1 and José María Gómez Hidalgo 2 1 Universidad
More informationProbabilistic Latent Semantic Analysis
Probabilistic Latent Semantic Analysis Thomas Hofmann Presentation by Ioannis Pavlopoulos & Andreas Damianou for the course of Data Mining & Exploration 1 Outline Latent Semantic Analysis o Need o Overview
More informationSTT 231 Test 1. Fill in the Letter of Your Choice to Each Question in the Scantron. Each question is worth 2 point.
STT 231 Test 1 Fill in the Letter of Your Choice to Each Question in the Scantron. Each question is worth 2 point. 1. A professor has kept records on grades that students have earned in his class. If he
More informationModel Ensemble for Click Prediction in Bing Search Ads
Model Ensemble for Click Prediction in Bing Search Ads Xiaoliang Ling Microsoft Bing xiaoling@microsoft.com Hucheng Zhou Microsoft Research huzho@microsoft.com Weiwei Deng Microsoft Bing dedeng@microsoft.com
More informationUsing dialogue context to improve parsing performance in dialogue systems
Using dialogue context to improve parsing performance in dialogue systems Ivan Meza-Ruiz and Oliver Lemon School of Informatics, Edinburgh University 2 Buccleuch Place, Edinburgh I.V.Meza-Ruiz@sms.ed.ac.uk,
More informationAustralian Journal of Basic and Applied Sciences
AENSI Journals Australian Journal of Basic and Applied Sciences ISSN:1991-8178 Journal home page: www.ajbasweb.com Feature Selection Technique Using Principal Component Analysis For Improving Fuzzy C-Mean
More informationHuman Emotion Recognition From Speech
RESEARCH ARTICLE OPEN ACCESS Human Emotion Recognition From Speech Miss. Aparna P. Wanare*, Prof. Shankar N. Dandare *(Department of Electronics & Telecommunication Engineering, Sant Gadge Baba Amravati
More informationOPTIMIZATINON OF TRAINING SETS FOR HEBBIAN-LEARNING- BASED CLASSIFIERS
OPTIMIZATINON OF TRAINING SETS FOR HEBBIAN-LEARNING- BASED CLASSIFIERS Václav Kocian, Eva Volná, Michal Janošek, Martin Kotyrba University of Ostrava Department of Informatics and Computers Dvořákova 7,
More informationLearning Methods for Fuzzy Systems
Learning Methods for Fuzzy Systems Rudolf Kruse and Andreas Nürnberger Department of Computer Science, University of Magdeburg Universitätsplatz, D-396 Magdeburg, Germany Phone : +49.39.67.876, Fax : +49.39.67.8
More informationSwitchboard Language Model Improvement with Conversational Data from Gigaword
Katholieke Universiteit Leuven Faculty of Engineering Master in Artificial Intelligence (MAI) Speech and Language Technology (SLT) Switchboard Language Model Improvement with Conversational Data from Gigaword
More informationINPE São José dos Campos
INPE-5479 PRE/1778 MONLINEAR ASPECTS OF DATA INTEGRATION FOR LAND COVER CLASSIFICATION IN A NEDRAL NETWORK ENVIRONNENT Maria Suelena S. Barros Valter Rodrigues INPE São José dos Campos 1993 SECRETARIA
More informationTruth Inference in Crowdsourcing: Is the Problem Solved?
Truth Inference in Crowdsourcing: Is the Problem Solved? Yudian Zheng, Guoliang Li #, Yuanbing Li #, Caihua Shan, Reynold Cheng # Department of Computer Science, Tsinghua University Department of Computer
More informationInteractive Whiteboard
50 Graphic Organizers for the Interactive Whiteboard Whiteboard-ready graphic organizers for reading, writing, math, and more to make learning engaging and interactive by Jennifer Jacobson & Dottie Raymer
More informationCalibration of Confidence Measures in Speech Recognition
Submitted to IEEE Trans on Audio, Speech, and Language, July 2010 1 Calibration of Confidence Measures in Speech Recognition Dong Yu, Senior Member, IEEE, Jinyu Li, Member, IEEE, Li Deng, Fellow, IEEE
More informationWHEN THERE IS A mismatch between the acoustic
808 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 14, NO. 3, MAY 2006 Optimization of Temporal Filters for Constructing Robust Features in Speech Recognition Jeih-Weih Hung, Member,
More informationAssignment 1: Predicting Amazon Review Ratings
Assignment 1: Predicting Amazon Review Ratings 1 Dataset Analysis Richard Park r2park@acsmail.ucsd.edu February 23, 2015 The dataset selected for this assignment comes from the set of Amazon reviews for
More informationThe 9 th International Scientific Conference elearning and software for Education Bucharest, April 25-26, / X
The 9 th International Scientific Conference elearning and software for Education Bucharest, April 25-26, 2013 10.12753/2066-026X-13-154 DATA MINING SOLUTIONS FOR DETERMINING STUDENT'S PROFILE Adela BÂRA,
More informationOCR for Arabic using SIFT Descriptors With Online Failure Prediction
OCR for Arabic using SIFT Descriptors With Online Failure Prediction Andrey Stolyarenko, Nachum Dershowitz The Blavatnik School of Computer Science Tel Aviv University Tel Aviv, Israel Email: stloyare@tau.ac.il,
More informationWE GAVE A LAWYER BASIC MATH SKILLS, AND YOU WON T BELIEVE WHAT HAPPENED NEXT
WE GAVE A LAWYER BASIC MATH SKILLS, AND YOU WON T BELIEVE WHAT HAPPENED NEXT PRACTICAL APPLICATIONS OF RANDOM SAMPLING IN ediscovery By Matthew Verga, J.D. INTRODUCTION Anyone who spends ample time working
More informationSpeech Recognition at ICSI: Broadcast News and beyond
Speech Recognition at ICSI: Broadcast News and beyond Dan Ellis International Computer Science Institute, Berkeley CA Outline 1 2 3 The DARPA Broadcast News task Aspects of ICSI
More informationCorrective Feedback and Persistent Learning for Information Extraction
Corrective Feedback and Persistent Learning for Information Extraction Aron Culotta a, Trausti Kristjansson b, Andrew McCallum a, Paul Viola c a Dept. of Computer Science, University of Massachusetts,
More informationSoftprop: Softmax Neural Network Backpropagation Learning
Softprop: Softmax Neural Networ Bacpropagation Learning Michael Rimer Computer Science Department Brigham Young University Provo, UT 84602, USA E-mail: mrimer@axon.cs.byu.edu Tony Martinez Computer Science
More informationLearning From the Past with Experiment Databases
Learning From the Past with Experiment Databases Joaquin Vanschoren 1, Bernhard Pfahringer 2, and Geoff Holmes 2 1 Computer Science Dept., K.U.Leuven, Leuven, Belgium 2 Computer Science Dept., University
More informationCS 446: Machine Learning
CS 446: Machine Learning Introduction to LBJava: a Learning Based Programming Language Writing classifiers Christos Christodoulopoulos Parisa Kordjamshidi Motivation 2 Motivation You still have not learnt
More informationAffective Classification of Generic Audio Clips using Regression Models
Affective Classification of Generic Audio Clips using Regression Models Nikolaos Malandrakis 1, Shiva Sundaram, Alexandros Potamianos 3 1 Signal Analysis and Interpretation Laboratory (SAIL), USC, Los
More informationModeling user preferences and norms in context-aware systems
Modeling user preferences and norms in context-aware systems Jonas Nilsson, Cecilia Lindmark Jonas Nilsson, Cecilia Lindmark VT 2016 Bachelor's thesis for Computer Science, 15 hp Supervisor: Juan Carlos
More informationTRANSFER LEARNING IN MIR: SHARING LEARNED LATENT REPRESENTATIONS FOR MUSIC AUDIO CLASSIFICATION AND SIMILARITY
TRANSFER LEARNING IN MIR: SHARING LEARNED LATENT REPRESENTATIONS FOR MUSIC AUDIO CLASSIFICATION AND SIMILARITY Philippe Hamel, Matthew E. P. Davies, Kazuyoshi Yoshii and Masataka Goto National Institute
More informationMachine Learning from Garden Path Sentences: The Application of Computational Linguistics
Machine Learning from Garden Path Sentences: The Application of Computational Linguistics http://dx.doi.org/10.3991/ijet.v9i6.4109 J.L. Du 1, P.F. Yu 1 and M.L. Li 2 1 Guangdong University of Foreign Studies,
More informationExploration. CS : Deep Reinforcement Learning Sergey Levine
Exploration CS 294-112: Deep Reinforcement Learning Sergey Levine Class Notes 1. Homework 4 due on Wednesday 2. Project proposal feedback sent Today s Lecture 1. What is exploration? Why is it a problem?
More informationSemi-supervised methods of text processing, and an application to medical concept extraction. Yacine Jernite Text-as-Data series September 17.
Semi-supervised methods of text processing, and an application to medical concept extraction Yacine Jernite Text-as-Data series September 17. 2015 What do we want from text? 1. Extract information 2. Link
More informationSemi-Supervised Face Detection
Semi-Supervised Face Detection Nicu Sebe, Ira Cohen 2, Thomas S. Huang 3, Theo Gevers Faculty of Science, University of Amsterdam, The Netherlands 2 HP Research Labs, USA 3 Beckman Institute, University
More informationThe Internet as a Normative Corpus: Grammar Checking with a Search Engine
The Internet as a Normative Corpus: Grammar Checking with a Search Engine Jonas Sjöbergh KTH Nada SE-100 44 Stockholm, Sweden jsh@nada.kth.se Abstract In this paper some methods using the Internet as a
More informationarxiv: v1 [cs.cv] 10 May 2017
Inferring and Executing Programs for Visual Reasoning Justin Johnson 1 Bharath Hariharan 2 Laurens van der Maaten 2 Judy Hoffman 1 Li Fei-Fei 1 C. Lawrence Zitnick 2 Ross Girshick 2 1 Stanford University
More informationReducing Features to Improve Bug Prediction
Reducing Features to Improve Bug Prediction Shivkumar Shivaji, E. James Whitehead, Jr., Ram Akella University of California Santa Cruz {shiv,ejw,ram}@soe.ucsc.edu Sunghun Kim Hong Kong University of Science
More informationAnalysis of Emotion Recognition System through Speech Signal Using KNN & GMM Classifier
IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-issn: 2278-2834,p- ISSN: 2278-8735.Volume 10, Issue 2, Ver.1 (Mar - Apr.2015), PP 55-61 www.iosrjournals.org Analysis of Emotion
More informationWord Segmentation of Off-line Handwritten Documents
Word Segmentation of Off-line Handwritten Documents Chen Huang and Sargur N. Srihari {chuang5, srihari}@cedar.buffalo.edu Center of Excellence for Document Analysis and Recognition (CEDAR), Department
More informationAUTOMATIC DETECTION OF PROLONGED FRICATIVE PHONEMES WITH THE HIDDEN MARKOV MODELS APPROACH 1. INTRODUCTION
JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 11/2007, ISSN 1642-6037 Marek WIŚNIEWSKI *, Wiesława KUNISZYK-JÓŹKOWIAK *, Elżbieta SMOŁKA *, Waldemar SUSZYŃSKI * HMM, recognition, speech, disorders
More informationA Simple VQA Model with a Few Tricks and Image Features from Bottom-up Attention
A Simple VQA Model with a Few Tricks and Image Features from Bottom-up Attention Damien Teney 1, Peter Anderson 2*, David Golub 4*, Po-Sen Huang 3, Lei Zhang 3, Xiaodong He 3, Anton van den Hengel 1 1
More informationThe Good Judgment Project: A large scale test of different methods of combining expert predictions
The Good Judgment Project: A large scale test of different methods of combining expert predictions Lyle Ungar, Barb Mellors, Jon Baron, Phil Tetlock, Jaime Ramos, Sam Swift The University of Pennsylvania
More informationTwitter Sentiment Classification on Sanders Data using Hybrid Approach
IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 17, Issue 4, Ver. I (July Aug. 2015), PP 118-123 www.iosrjournals.org Twitter Sentiment Classification on Sanders
More informationMulti-label classification via multi-target regression on data streams
Mach Learn (2017) 106:745 770 DOI 10.1007/s10994-016-5613-5 Multi-label classification via multi-target regression on data streams Aljaž Osojnik 1,2 Panče Panov 1 Sašo Džeroski 1,2,3 Received: 26 April
More informationPhonetic- and Speaker-Discriminant Features for Speaker Recognition. Research Project
Phonetic- and Speaker-Discriminant Features for Speaker Recognition by Lara Stoll Research Project Submitted to the Department of Electrical Engineering and Computer Sciences, University of California
More informationSpeech Emotion Recognition Using Support Vector Machine
Speech Emotion Recognition Using Support Vector Machine Yixiong Pan, Peipei Shen and Liping Shen Department of Computer Technology Shanghai JiaoTong University, Shanghai, China panyixiong@sjtu.edu.cn,
More informationLecture 2: Quantifiers and Approximation
Lecture 2: Quantifiers and Approximation Case study: Most vs More than half Jakub Szymanik Outline Number Sense Approximate Number Sense Approximating most Superlative Meaning of most What About Counting?
More informationSoftware Maintenance
1 What is Software Maintenance? Software Maintenance is a very broad activity that includes error corrections, enhancements of capabilities, deletion of obsolete capabilities, and optimization. 2 Categories
More informationAxiom 2013 Team Description Paper
Axiom 2013 Team Description Paper Mohammad Ghazanfari, S Omid Shirkhorshidi, Farbod Samsamipour, Hossein Rahmatizadeh Zagheli, Mohammad Mahdavi, Payam Mohajeri, S Abbas Alamolhoda Robotics Scientific Association
More informationUsing Web Searches on Important Words to Create Background Sets for LSI Classification
Using Web Searches on Important Words to Create Background Sets for LSI Classification Sarah Zelikovitz and Marina Kogan College of Staten Island of CUNY 2800 Victory Blvd Staten Island, NY 11314 Abstract
More informationThe Evolution of Random Phenomena
The Evolution of Random Phenomena A Look at Markov Chains Glen Wang glenw@uchicago.edu Splash! Chicago: Winter Cascade 2012 Lecture 1: What is Randomness? What is randomness? Can you think of some examples
More informationLearning to Rank with Selection Bias in Personal Search
Learning to Rank with Selection Bias in Personal Search Xuanhui Wang, Michael Bendersky, Donald Metzler, Marc Najork Google Inc. Mountain View, CA 94043 {xuanhui, bemike, metzler, najork}@google.com ABSTRACT
More informationIndian Institute of Technology, Kanpur
Indian Institute of Technology, Kanpur Course Project - CS671A POS Tagging of Code Mixed Text Ayushman Sisodiya (12188) {ayushmn@iitk.ac.in} Donthu Vamsi Krishna (15111016) {vamsi@iitk.ac.in} Sandeep Kumar
More informationPREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES
PREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES Po-Sen Huang, Kshitiz Kumar, Chaojun Liu, Yifan Gong, Li Deng Department of Electrical and Computer Engineering,
More informationMGT/MGP/MGB 261: Investment Analysis
UNIVERSITY OF CALIFORNIA, DAVIS GRADUATE SCHOOL OF MANAGEMENT SYLLABUS for Fall 2014 MGT/MGP/MGB 261: Investment Analysis Daytime MBA: Tu 12:00p.m. - 3:00 p.m. Location: 1302 Gallagher (CRN: 51489) Sacramento
More informationGrade 2: Using a Number Line to Order and Compare Numbers Place Value Horizontal Content Strand
Grade 2: Using a Number Line to Order and Compare Numbers Place Value Horizontal Content Strand Texas Essential Knowledge and Skills (TEKS): (2.1) Number, operation, and quantitative reasoning. The student
More informationSemantic Segmentation with Histological Image Data: Cancer Cell vs. Stroma
Semantic Segmentation with Histological Image Data: Cancer Cell vs. Stroma Adam Abdulhamid Stanford University 450 Serra Mall, Stanford, CA 94305 adama94@cs.stanford.edu Abstract With the introduction
More informationSeminar - Organic Computing
Seminar - Organic Computing Self-Organisation of OC-Systems Markus Franke 25.01.2006 Typeset by FoilTEX Timetable 1. Overview 2. Characteristics of SO-Systems 3. Concern with Nature 4. Design-Concepts
More informationMedical Complexity: A Pragmatic Theory
http://eoimages.gsfc.nasa.gov/images/imagerecords/57000/57747/cloud_combined_2048.jpg Medical Complexity: A Pragmatic Theory Chris Feudtner, MD PhD MPH The Children s Hospital of Philadelphia Main Thesis
More informationBeyond the Pipeline: Discrete Optimization in NLP
Beyond the Pipeline: Discrete Optimization in NLP Tomasz Marciniak and Michael Strube EML Research ggmbh Schloss-Wolfsbrunnenweg 33 69118 Heidelberg, Germany http://www.eml-research.de/nlp Abstract We
More informationSpeech Segmentation Using Probabilistic Phonetic Feature Hierarchy and Support Vector Machines
Speech Segmentation Using Probabilistic Phonetic Feature Hierarchy and Support Vector Machines Amit Juneja and Carol Espy-Wilson Department of Electrical and Computer Engineering University of Maryland,
More informationGreen Belt Curriculum (This workshop can also be conducted on-site, subject to price change and number of participants)
Green Belt Curriculum (This workshop can also be conducted on-site, subject to price change and number of participants) Notes: 1. We use Mini-Tab in this workshop. Mini-tab is available for free trail
More informationModeling function word errors in DNN-HMM based LVCSR systems
Modeling function word errors in DNN-HMM based LVCSR systems Melvin Jose Johnson Premkumar, Ankur Bapna and Sree Avinash Parchuri Department of Computer Science Department of Electrical Engineering Stanford
More informationThe University of Amsterdam s Concept Detection System at ImageCLEF 2011
The University of Amsterdam s Concept Detection System at ImageCLEF 2011 Koen E. A. van de Sande and Cees G. M. Snoek Intelligent Systems Lab Amsterdam, University of Amsterdam Software available from:
More informationA Bootstrapping Model of Frequency and Context Effects in Word Learning
Cognitive Science 41 (2017) 590 622 Copyright 2016 Cognitive Science Society, Inc. All rights reserved. ISSN: 0364-0213 print / 1551-6709 online DOI: 10.1111/cogs.12353 A Bootstrapping Model of Frequency
More informationOn-the-Fly Customization of Automated Essay Scoring
Research Report On-the-Fly Customization of Automated Essay Scoring Yigal Attali Research & Development December 2007 RR-07-42 On-the-Fly Customization of Automated Essay Scoring Yigal Attali ETS, Princeton,
More informationRadius STEM Readiness TM
Curriculum Guide Radius STEM Readiness TM While today s teens are surrounded by technology, we face a stark and imminent shortage of graduates pursuing careers in Science, Technology, Engineering, and
More informationhave to be modeled) or isolated words. Output of the system is a grapheme-tophoneme conversion system which takes as its input the spelling of words,
A Language-Independent, Data-Oriented Architecture for Grapheme-to-Phoneme Conversion Walter Daelemans and Antal van den Bosch Proceedings ESCA-IEEE speech synthesis conference, New York, September 1994
More informationIEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 3, MARCH
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 3, MARCH 2009 423 Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition George
More informationMathematics Success Grade 7
T894 Mathematics Success Grade 7 [OBJECTIVE] The student will find probabilities of compound events using organized lists, tables, tree diagrams, and simulations. [PREREQUISITE SKILLS] Simple probability,
More informationMandarin Lexical Tone Recognition: The Gating Paradigm
Kansas Working Papers in Linguistics, Vol. 0 (008), p. 8 Abstract Mandarin Lexical Tone Recognition: The Gating Paradigm Yuwen Lai and Jie Zhang University of Kansas Research on spoken word recognition
More informationWhy Did My Detector Do That?!
Why Did My Detector Do That?! Predicting Keystroke-Dynamics Error Rates Kevin Killourhy and Roy Maxion Dependable Systems Laboratory Computer Science Department Carnegie Mellon University 5000 Forbes Ave,
More informationClass-Discriminative Weighted Distortion Measure for VQ-Based Speaker Identification
Class-Discriminative Weighted Distortion Measure for VQ-Based Speaker Identification Tomi Kinnunen and Ismo Kärkkäinen University of Joensuu, Department of Computer Science, P.O. Box 111, 80101 JOENSUU,
More informationLip reading: Japanese vowel recognition by tracking temporal changes of lip shape
Lip reading: Japanese vowel recognition by tracking temporal changes of lip shape Koshi Odagiri 1, and Yoichi Muraoka 1 1 Graduate School of Fundamental/Computer Science and Engineering, Waseda University,
More informationUniversidade do Minho Escola de Engenharia
Universidade do Minho Escola de Engenharia Universidade do Minho Escola de Engenharia Dissertação de Mestrado Knowledge Discovery is the nontrivial extraction of implicit, previously unknown, and potentially
More informationarxiv: v1 [cs.cl] 2 Apr 2017
Word-Alignment-Based Segment-Level Machine Translation Evaluation using Word Embeddings Junki Matsuo and Mamoru Komachi Graduate School of System Design, Tokyo Metropolitan University, Japan matsuo-junki@ed.tmu.ac.jp,
More informationLearning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models
Learning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models Stephan Gouws and GJ van Rooyen MIH Medialab, Stellenbosch University SOUTH AFRICA {stephan,gvrooyen}@ml.sun.ac.za
More informationSouth Carolina College- and Career-Ready Standards for Mathematics. Standards Unpacking Documents Grade 5
South Carolina College- and Career-Ready Standards for Mathematics Standards Unpacking Documents Grade 5 South Carolina College- and Career-Ready Standards for Mathematics Standards Unpacking Documents
More informationTIMSS ADVANCED 2015 USER GUIDE FOR THE INTERNATIONAL DATABASE. Pierre Foy
TIMSS ADVANCED 2015 USER GUIDE FOR THE INTERNATIONAL DATABASE Pierre Foy TIMSS Advanced 2015 orks User Guide for the International Database Pierre Foy Contributors: Victoria A.S. Centurino, Kerry E. Cotter,
More informationCultivating DNN Diversity for Large Scale Video Labelling
Cultivating DNN Diversity for Large Scale Video Labelling Mikel Bober-Irizar mikel@mxbi.net Sameed Husain sameed.husain@surrey.ac.uk Miroslaw Bober m.bober@surrey.ac.uk Eng-Jon Ong e.ong@surrey.ac.uk Abstract
More informationThe stages of event extraction
The stages of event extraction David Ahn Intelligent Systems Lab Amsterdam University of Amsterdam ahn@science.uva.nl Abstract Event detection and recognition is a complex task consisting of multiple sub-tasks
More informationMathematics process categories
Mathematics process categories All of the UK curricula define multiple categories of mathematical proficiency that require students to be able to use and apply mathematics, beyond simple recall of facts
More information