Data Mining & Machine Learning
|
|
- Pauline Ward
- 5 years ago
- Views:
Transcription
1 Data Mining & Machine Learning CS57300 Purdue University April 10,
2 Predicting Sequences 2
3 But first, a detour to Noise Contrastive Estimation 3
4 } Machine learning methods are much better at classifying examples than generating new ones In classification tasks, we use the exact derivatives to find a solution that maximizes the likelihood In generative tasks, we can only compute an estimate of the derivative } Because we have better techniques to classify data than to generate data Can we make generative tasks look more like classification tasks? Bruno Ribeiro 4
5 Learn a Classifier to Distinguishing Noise from Data This is key idea behind noise contrastive estimation (NCE): make generative tasks look like classification tasks Pioneered by Hastie, Tibshirani, Friedman in The Elements of Statistical Learning in 2008, Section Unsupervised Learning as Supervised Learning The idea is quite simple, consider the task of learning to distinguish noise from the data, i.e., search for a good classifier f(x ;W) Label y 1 =1 (= true data) Training Data Examples Classifier. x 1 = x 2 = Random Noise Examples Label y=0 (= false data) True example generator: : noise generator 5
6 Generation Task Using Classifier Now use the learned classifier (which distinguishes noise from the data) to generate new data but how? Naïve approach: Generate examples from the random noise whatever gets classified as real data will be our generated examples x 1 = Random Noise Examples x 2 = What is the problem with this naïve approach? In very high dimensions (e.g., images), true random noise will not generate any interesting examples x 1 x 2 x 3 6
7 Go to ipython notebook 7
8 Back to sequences 8
9 Sequences } In this lecture we will focus on word sequences (a.k.a. text) } The techniques we see are applicable to any type of sequence } A sequence is a succession of elements from a set (likely finite) } We will write a sequence of n elements as x 1,, x n } The temporal ordering is key to learning the sequence 9
10 2017 Bruno Ribeiro Word Sequences Rank-3 word embedding } Embed words w.r.t. their sentences Bring me a constant woman to her husband Forgetting, like a good man your late censure of his wife } Under the Markov assumption P[bring, me, a, constant, woman, to, her, husband] = P[bring]P[me bring] P[a me] P[constant a] P[husband her] Go to ipython notebook
11 2017 Bruno Ribeiro Word Sequences & Embeddings Rank-3 word embedding } Embed words w.r.t. their sentences Bring me a constant woman to her husband Forgetting, like a good man your late censure of his wife husband man wife woman } Initial idea by (Chen et al. 2012) was named Latent Markov Embedding, rediscovered by (Mikolov et al. 2013) named word2vec } Main difference: Application: (Mikolov et al. 2013) paid attention to the composition of latent vectors in sentences Otherwise, techniques equivalent Chen, S., Moore, J. L., Turnbull, D., & Joachims, T. (2012). Playlist prediction via metric embedding. In ACM SIGKDD. Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. In NIPS
12 2017 Bruno Ribeiro Word2vec Embeddings Rank-3 word embedding How the math works Bring me a constant woman to her husband Forgetting, like a good man your late censure of his wife husband man woman wife } Conditional bag-of-words assumption (SKIPGRAM): All words are independent given the target word P[bring, constant, husband woman] = P[bring woman] P[constant woman] P[husband woman] P[forgetting, like, good, late, censure, wife man] = P[forgetting man] P[like man] P[good man] P[late man] P[censure man] P[wife man]
13 Word2vec Type Embeddings III 1 st coordinate of output words 2 nd coord. of output words exp X = 1 st coordinate of conditional word σ 1 u 1 woman v 1 husband + Embedding of woman as conditional word 2 nd coordinate of conditional word σ 2 u 2 woman v 2 husband The machine learning challenge is not summing over all words 2017 Bruno Ribeiro
14 <latexit sha1_base64="cipmw6+acjie9pp8tt1pqfh35g4=">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</latexit> <latexit sha1_base64="cipmw6+acjie9pp8tt1pqfh35g4=">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</latexit> <latexit sha1_base64="cipmw6+acjie9pp8tt1pqfh35g4=">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</latexit> <latexit sha1_base64="cipmw6+acjie9pp8tt1pqfh35g4=">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</latexit> <latexit sha1_base64="20r+kfvojzrfz60s1mdkdrhzzoq=">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</latexit> <latexit sha1_base64="20r+kfvojzrfz60s1mdkdrhzzoq=">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</latexit> <latexit sha1_base64="20r+kfvojzrfz60s1mdkdrhzzoq=">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</latexit> <latexit sha1_base64="sm8sxrapgkh1g+uhjbid190wsxc=">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</latexit> <latexit sha1_base64="sm8sxrapgkh1g+uhjbid190wsxc=">aaahjhic3vxdahqxfe7vrnx9a/vkvektc6u0y8yikeih4i3ghrxtd+wmjzm5oxs2mqxjpu02dd6nxuqlecdeeonl+ajmdoz1t9v2tkedw3w553w5j98jszrxpo3nfv+4dpnkyupq0rxm9rs3b91exrmzq2wukoxqyaxaj4ggzllymcxw2m8uebfx2iugl0r/3ieozwt6zowycavjutznlbhnoli+z4pxijymapgoglqi3rjekojgec3reoob54ffgzvuj+2dlcwfqsxplia1lbote76xmdaszrjludsdxeng6jak0ispwaztikch9nhcqyfbzh/jvltusw0ew6djlgitryjykykygt7tk41n+xq56t8lluuz3ebkq0t9ngmjcakjjpkcavjiauivc+vioickuooum8lsrm2k5lpozmqqzahkshfaslikfnztdrue1kyschypokzwd0gguioypk6d8x45mklw2pfv9ym3gng3latk4yhkiugap7lbq747blgkkslaqlvkm6pzctsdmklpu8jh0+v4ow22wi0mcqjun7eirz0zygmi29117yhe2mbt7zfovqdrwhphw+70oeemzd7jfdpioayx0zekaz5lyvuzt/1uzhx3kl5bxiu7enzjzo+e7l/itkzhvdufzlm6umfuvtslosfd44xt8u8joxgdq+gfe/7ntd3rldpt//op/z80nzlubkqlgrnbizazkgkkki/si2ygnalmtk39s52oaot4yprzn6zfzgcglm2lji/lc1jyolk5updm+kcfhxmw2+34rsdvhq9tva4fjcv0hz1abesjp2glvutbaadr9b59qj/q58bhxpfg18a3kvtsqs25i2zg48cv7ehvaw==</latexit> <latexit sha1_base64="sm8sxrapgkh1g+uhjbid190wsxc=">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</latexit> <latexit sha1_base64="sm8sxrapgkh1g+uhjbid190wsxc=">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</latexit> <latexit sha1_base64="6jplcbwszurx8pqdw+oaf+hhnae=">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</latexit> <latexit sha1_base64="6jplcbwszurx8pqdw+oaf+hhnae=">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</latexit> <latexit sha1_base64="6jplcbwszurx8pqdw+oaf+hhnae=">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</latexit> <latexit sha1_base64="6jplcbwszurx8pqdw+oaf+hhnae=">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</latexit> <latexit sha1_base64="rjx2viy0zv0wbbosgmdnfnknehm=">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</latexit> <latexit sha1_base64="rjx2viy0zv0wbbosgmdnfnknehm=">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</latexit> <latexit sha1_base64="rjx2viy0zv0wbbosgmdnfnknehm=">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</latexit> Matrix Factorization as a Neural Network (v2) But neural networks can have isomorphic network representations KX Matrix factorization: X U V T = Neural network representation: k=1 ku k v T k 4X X 1,7 = ku 1,k v 7,k k=1 Element-wise product Linear activation Linear activation u 1 v 1 U<latexit sha1_base64="20r+kfvojzrfz60s1mdkdrhzzoq=">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</latexit> V<latexit sha1_base64="rjx2viy0zv0wbbosgmdnfnknehm=">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</latexit> One-hot encoding of user One-hot encoding of product
15 <latexit sha1_base64="20r+kfvojzrfz60s1mdkdrhzzoq=">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</latexit> <latexit sha1_base64="20r+kfvojzrfz60s1mdkdrhzzoq=">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</latexit> <latexit sha1_base64="20r+kfvojzrfz60s1mdkdrhzzoq=">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</latexit> <latexit sha1_base64="rjx2viy0zv0wbbosgmdnfnknehm=">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</latexit> <latexit sha1_base64="rjx2viy0zv0wbbosgmdnfnknehm=">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</latexit> <latexit sha1_base64="rjx2viy0zv0wbbosgmdnfnknehm=">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</latexit> Word2vec Embedding as Neural Network Neural network representation of word2vec: Linear activation Linear activation u 1 v 1 U<latexit sha1_base64="20r+kfvojzrfz60s1mdkdrhzzoq=">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</latexit> V<latexit sha1_base64="rjx2viy0zv0wbbosgmdnfnknehm=">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</latexit> One-hot encoding of output word One-hot encoding of input word
Deep Learning Basics Lecture 10: Neural Language Models. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 10: Neural Language Models Princeton University COS 495 Instructor: Yingyu Liang Natural language Processing (NLP) The processing of the human languages by computers One of
More informationCS230: Lecture 8 Word2Vec applications + Recurrent Neural Networks with Attention
CS23: Lecture 8 Word2Vec applications + Recurrent Neural Networks with Attention Today s outline We will learn how to: I. Word Vector Representation i. Training - Generalize results with word vectors -
More informationword2vec Parameter Learning Explained
word2vec Parameter Learning Explained Xin Rong ronxin@umich.edu Abstract The word2vec model and application by Mikolov et al. have attracted a great amount of attention in recent two years. The vector
More informationDISTRIBUTIONAL SEMANTICS
COMP90042 LECTURE 4 DISTRIBUTIONAL SEMANTICS LEXICAL DATABASES - PROBLEMS Manually constructed Expensive Human annotation can be biased and noisy Language is dynamic New words: slangs, terminology, etc.
More informationBayesian Paragraph Vectors
Bayesian Paragraph Vectors Geng Ji 1, Robert Bamler 2, Erik B. Sudderth 1, and Stephan Mandt 2 1 Department of Computer Science, UC Irvine, {gji1, sudderth}@uci.edu 2 Disney Research, firstname.lastname@disneyresearch.com
More informationDeep Learning for NLP Part 2
Deep Learning for NLP Part 2 CS224N Christopher Manning (Many slides borrowed from ACL 2012/NAACL 2013 Tutorials by me, Richard Socher and Yoshua Bengio) 2 Part 1.3: The Basics Word Representations The
More informationSemantics with Dense Vectors. Reference: D. Jurafsky and J. Martin, Speech and Language Processing
Semantics with Dense Vectors Reference: D. Jurafsky and J. Martin, Speech and Language Processing 1 Semantics with Dense Vectors We saw how to represent a word as a sparse vector with dimensions corresponding
More informationRaRE: Social Rank Regulated Large-scale Network Embedding
RaRE: Social Rank Regulated Large-scale Network Embedding Authors: Yupeng Gu 1, Yizhou Sun 1, Yanen Li 2, Yang Yang 3 04/26/2018 The Web Conference, 2018 1 University of California, Los Angeles 2 Snapchat
More informationSparse vectors recap. ANLP Lecture 22 Lexical Semantics with Dense Vectors. Before density, another approach to normalisation.
ANLP Lecture 22 Lexical Semantics with Dense Vectors Henry S. Thompson Based on slides by Jurafsky & Martin, some via Dorota Glowacka 5 November 2018 Previous lectures: Sparse vectors recap How to represent
More informationANLP Lecture 22 Lexical Semantics with Dense Vectors
ANLP Lecture 22 Lexical Semantics with Dense Vectors Henry S. Thompson Based on slides by Jurafsky & Martin, some via Dorota Glowacka 5 November 2018 Henry S. Thompson ANLP Lecture 22 5 November 2018 Previous
More informationarxiv: v2 [cs.cl] 1 Jan 2019
Variational Self-attention Model for Sentence Representation arxiv:1812.11559v2 [cs.cl] 1 Jan 2019 Qiang Zhang 1, Shangsong Liang 2, Emine Yilmaz 1 1 University College London, London, United Kingdom 2
More informationAn overview of word2vec
An overview of word2vec Benjamin Wilson Berlin ML Meetup, July 8 2014 Benjamin Wilson word2vec Berlin ML Meetup 1 / 25 Outline 1 Introduction 2 Background & Significance 3 Architecture 4 CBOW word representations
More informationGenerative Clustering, Topic Modeling, & Bayesian Inference
Generative Clustering, Topic Modeling, & Bayesian Inference INFO-4604, Applied Machine Learning University of Colorado Boulder December 12-14, 2017 Prof. Michael Paul Unsupervised Naïve Bayes Last week
More informationHomework 3 COMS 4705 Fall 2017 Prof. Kathleen McKeown
Homework 3 COMS 4705 Fall 017 Prof. Kathleen McKeown The assignment consists of a programming part and a written part. For the programming part, make sure you have set up the development environment as
More informationDeep Learning Basics Lecture 7: Factor Analysis. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 7: Factor Analysis Princeton University COS 495 Instructor: Yingyu Liang Supervised v.s. Unsupervised Math formulation for supervised learning Given training data x i, y i
More informationNotes on Noise Contrastive Estimation (NCE)
Notes on Noise Contrastive Estimation NCE) David Meyer dmm@{-4-5.net,uoregon.edu,...} March 0, 207 Introduction In this note we follow the notation used in [2]. Suppose X x, x 2,, x Td ) is a sample of
More informationtext classification 3: neural networks
text classification 3: neural networks CS 585, Fall 2018 Introduction to Natural Language Processing http://people.cs.umass.edu/~miyyer/cs585/ Mohit Iyyer College of Information and Computer Sciences University
More informationSUPPORT VECTOR MACHINE
SUPPORT VECTOR MACHINE Mainly based on https://nlp.stanford.edu/ir-book/pdf/15svm.pdf 1 Overview SVM is a huge topic Integration of MMDS, IIR, and Andrew Moore s slides here Our foci: Geometric intuition
More informationWord2Vec Embedding. Embedding. Word Embedding 1.1 BEDORE. Word Embedding. 1.2 Embedding. Word Embedding. Embedding.
c Word Embedding Embedding Word2Vec Embedding Word EmbeddingWord2Vec 1. Embedding 1.1 BEDORE 0 1 BEDORE 113 0033 2 35 10 4F y katayama@bedore.jp Word Embedding Embedding 1.2 Embedding Embedding Word Embedding
More informationMachine Learning Linear Models
Machine Learning Linear Models Outline II - Linear Models 1. Linear Regression (a) Linear regression: History (b) Linear regression with Least Squares (c) Matrix representation and Normal Equation Method
More informationNeural Networks for NLP. COMP-599 Nov 30, 2016
Neural Networks for NLP COMP-599 Nov 30, 2016 Outline Neural networks and deep learning: introduction Feedforward neural networks word2vec Complex neural network architectures Convolutional neural networks
More informationMultivariate statistical methods and data mining in particle physics
Multivariate statistical methods and data mining in particle physics RHUL Physics www.pp.rhul.ac.uk/~cowan Academic Training Lectures CERN 16 19 June, 2008 1 Outline Statement of the problem Some general
More informationConditional Language Modeling. Chris Dyer
Conditional Language Modeling Chris Dyer Unconditional LMs A language model assigns probabilities to sequences of words,. w =(w 1,w 2,...,w`) It is convenient to decompose this probability using the chain
More informationNatural Language Processing with Deep Learning CS224N/Ling284. Richard Socher Lecture 2: Word Vectors
Natural Language Processing with Deep Learning CS224N/Ling284 Richard Socher Lecture 2: Word Vectors Organization PSet 1 is released. Coding Session 1/22: (Monday, PA1 due Thursday) Some of the questions
More informationWord Embeddings 2 - Class Discussions
Word Embeddings 2 - Class Discussions Jalaj February 18, 2016 Opening Remarks - Word embeddings as a concept are intriguing. The approaches are mostly adhoc but show good empirical performance. Paper 1
More informationarxiv: v3 [cs.cl] 30 Jan 2016
word2vec Parameter Learning Explained Xin Rong ronxin@umich.edu arxiv:1411.2738v3 [cs.cl] 30 Jan 2016 Abstract The word2vec model and application by Mikolov et al. have attracted a great amount of attention
More informationGloVe: Global Vectors for Word Representation 1
GloVe: Global Vectors for Word Representation 1 J. Pennington, R. Socher, C.D. Manning M. Korniyenko, S. Samson Deep Learning for NLP, 13 Jun 2017 1 https://nlp.stanford.edu/projects/glove/ Outline Background
More informationCOMP 551 Applied Machine Learning Lecture 13: Dimension reduction and feature selection
COMP 551 Applied Machine Learning Lecture 13: Dimension reduction and feature selection Instructor: Herke van Hoof (herke.vanhoof@cs.mcgill.ca) Based on slides by:, Jackie Chi Kit Cheung Class web page:
More informationPart-of-Speech Tagging + Neural Networks 3: Word Embeddings CS 287
Part-of-Speech Tagging + Neural Networks 3: Word Embeddings CS 287 Review: Neural Networks One-layer multi-layer perceptron architecture, NN MLP1 (x) = g(xw 1 + b 1 )W 2 + b 2 xw + b; perceptron x is the
More informationCS Lecture 18. Topic Models and LDA
CS 6347 Lecture 18 Topic Models and LDA (some slides by David Blei) Generative vs. Discriminative Models Recall that, in Bayesian networks, there could be many different, but equivalent models of the same
More informationJoint Emotion Analysis via Multi-task Gaussian Processes
Joint Emotion Analysis via Multi-task Gaussian Processes Daniel Beck, Trevor Cohn, Lucia Specia October 28, 2014 1 Introduction 2 Multi-task Gaussian Process Regression 3 Experiments and Discussion 4 Conclusions
More informationNatural Language Processing
SFU NatLangLab Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class Simon Fraser University October 9, 2018 0 Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class
More informationNEURAL LANGUAGE MODELS
COMP90042 LECTURE 14 NEURAL LANGUAGE MODELS LANGUAGE MODELS Assign a probability to a sequence of words Framed as sliding a window over the sentence, predicting each word from finite context to left E.g.,
More informationCME323 Distributed Algorithms and Optimization. GloVe on Spark. Alex Adamson SUNet ID: aadamson. June 6, 2016
GloVe on Spark Alex Adamson SUNet ID: aadamson June 6, 2016 Introduction Pennington et al. proposes a novel word representation algorithm called GloVe (Global Vectors for Word Representation) that synthesizes
More informationLearning Features from Co-occurrences: A Theoretical Analysis
Learning Features from Co-occurrences: A Theoretical Analysis Yanpeng Li IBM T. J. Watson Research Center Yorktown Heights, New York 10598 liyanpeng.lyp@gmail.com Abstract Representing a word by its co-occurrences
More informationSupport Vector Machines: Kernels
Support Vector Machines: Kernels CS6780 Advanced Machine Learning Spring 2015 Thorsten Joachims Cornell University Reading: Murphy 14.1, 14.2, 14.4 Schoelkopf/Smola Chapter 7.4, 7.6, 7.8 Non-Linear Problems
More informationAn Introduction to Statistical and Probabilistic Linear Models
An Introduction to Statistical and Probabilistic Linear Models Maximilian Mozes Proseminar Data Mining Fakultät für Informatik Technische Universität München June 07, 2017 Introduction In statistical learning
More informationHidden Markov Models
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Hidden Markov Models Matt Gormley Lecture 22 April 2, 2018 1 Reminders Homework
More informationLogic and machine learning review. CS 540 Yingyu Liang
Logic and machine learning review CS 540 Yingyu Liang Propositional logic Logic If the rules of the world are presented formally, then a decision maker can use logical reasoning to make rational decisions.
More informationSequence Models. Ji Yang. Department of Computing Science, University of Alberta. February 14, 2018
Sequence Models Ji Yang Department of Computing Science, University of Alberta February 14, 2018 This is a note mainly based on Prof. Andrew Ng s MOOC Sequential Models. I also include materials (equations,
More informationTowards Universal Sentence Embeddings
Towards Universal Sentence Embeddings Towards Universal Paraphrastic Sentence Embeddings J. Wieting, M. Bansal, K. Gimpel and K. Livescu, ICLR 2016 A Simple But Tough-To-Beat Baseline For Sentence Embeddings
More informationSupport Vector Machines. CAP 5610: Machine Learning Instructor: Guo-Jun QI
Support Vector Machines CAP 5610: Machine Learning Instructor: Guo-Jun QI 1 Linear Classifier Naive Bayes Assume each attribute is drawn from Gaussian distribution with the same variance Generative model:
More informationLecture 5 Neural models for NLP
CS546: Machine Learning in NLP (Spring 2018) http://courses.engr.illinois.edu/cs546/ Lecture 5 Neural models for NLP Julia Hockenmaier juliahmr@illinois.edu 3324 Siebel Center Office hours: Tue/Thu 2pm-3pm
More informationMethods and Criteria for Model Selection. CS57300 Data Mining Fall Instructor: Bruno Ribeiro
Methods and Criteria for Model Selection CS57300 Data Mining Fall 2016 Instructor: Bruno Ribeiro Goal } Introduce classifier evaluation criteria } Introduce Bias x Variance duality } Model Assessment }
More informationRegularization Introduction to Machine Learning. Matt Gormley Lecture 10 Feb. 19, 2018
1-61 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Regularization Matt Gormley Lecture 1 Feb. 19, 218 1 Reminders Homework 4: Logistic
More informationMIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October,
MIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October, 23 2013 The exam is closed book. You are allowed a one-page cheat sheet. Answer the questions in the spaces provided on the question sheets. If you run
More informationData Mining. CS57300 Purdue University. Bruno Ribeiro. February 8, 2018
Data Mining CS57300 Purdue University Bruno Ribeiro February 8, 2018 Decision trees Why Trees? interpretable/intuitive, popular in medical applications because they mimic the way a doctor thinks model
More informationDimension Reduction (PCA, ICA, CCA, FLD,
Dimension Reduction (PCA, ICA, CCA, FLD, Topic Models) Yi Zhang 10-701, Machine Learning, Spring 2011 April 6 th, 2011 Parts of the PCA slides are from previous 10-701 lectures 1 Outline Dimension reduction
More informationMachine Learning. B. Unsupervised Learning B.2 Dimensionality Reduction. Lars Schmidt-Thieme, Nicolas Schilling
Machine Learning B. Unsupervised Learning B.2 Dimensionality Reduction Lars Schmidt-Thieme, Nicolas Schilling Information Systems and Machine Learning Lab (ISMLL) Institute for Computer Science University
More informationOnline Videos FERPA. Sign waiver or sit on the sides or in the back. Off camera question time before and after lecture. Questions?
Online Videos FERPA Sign waiver or sit on the sides or in the back Off camera question time before and after lecture Questions? Lecture 1, Slide 1 CS224d Deep NLP Lecture 4: Word Window Classification
More informationLecture 6: Neural Networks for Representing Word Meaning
Lecture 6: Neural Networks for Representing Word Meaning Mirella Lapata School of Informatics University of Edinburgh mlap@inf.ed.ac.uk February 7, 2017 1 / 28 Logistic Regression Input is a feature vector,
More informationUVA CS / Introduc8on to Machine Learning and Data Mining. Lecture 9: Classifica8on with Support Vector Machine (cont.
UVA CS 4501-001 / 6501 007 Introduc8on to Machine Learning and Data Mining Lecture 9: Classifica8on with Support Vector Machine (cont.) Yanjun Qi / Jane University of Virginia Department of Computer Science
More informationRecap from previous lecture
Recap from previous lecture Learning is using past experience to improve future performance. Different types of learning: supervised unsupervised reinforcement active online... For a machine, experience
More informationIntroduction to machine learning and pattern recognition Lecture 2 Coryn Bailer-Jones
Introduction to machine learning and pattern recognition Lecture 2 Coryn Bailer-Jones http://www.mpia.de/homes/calj/mlpr_mpia2008.html 1 1 Last week... supervised and unsupervised methods need adaptive
More informationMachine Learning for Data Science (CS4786) Lecture 12
Machine Learning for Data Science (CS4786) Lecture 12 Gaussian Mixture Models Course Webpage : http://www.cs.cornell.edu/courses/cs4786/2016fa/ Back to K-means Single link is sensitive to outliners We
More informationTopics in Natural Language Processing
Topics in Natural Language Processing Shay Cohen Institute for Language, Cognition and Computation University of Edinburgh Lecture 9 Administrativia Next class will be a summary Please email me questions
More informationESANN'2003 proceedings - European Symposium on Artificial Neural Networks Bruges (Belgium), April 2003, d-side publi., ISBN X, pp.
On different ensembles of kernel machines Michiko Yamana, Hiroyuki Nakahara, Massimiliano Pontil, and Shun-ichi Amari Λ Abstract. We study some ensembles of kernel machines. Each machine is first trained
More informationInformation Extraction from Text
Information Extraction from Text Jing Jiang Chapter 2 from Mining Text Data (2012) Presented by Andrew Landgraf, September 13, 2013 1 What is Information Extraction? Goal is to discover structured information
More informationCS 6375 Machine Learning
CS 6375 Machine Learning Nicholas Ruozzi University of Texas at Dallas Slides adapted from David Sontag and Vibhav Gogate Course Info. Instructor: Nicholas Ruozzi Office: ECSS 3.409 Office hours: Tues.
More informationArtificial Neural Networks D B M G. Data Base and Data Mining Group of Politecnico di Torino. Elena Baralis. Politecnico di Torino
Artificial Neural Networks Data Base and Data Mining Group of Politecnico di Torino Elena Baralis Politecnico di Torino Artificial Neural Networks Inspired to the structure of the human brain Neurons as
More informationNeural Word Embeddings from Scratch
Neural Word Embeddings from Scratch Xin Li 12 1 NLP Center Tencent AI Lab 2 Dept. of System Engineering & Engineering Management The Chinese University of Hong Kong 2018-04-09 Xin Li Neural Word Embeddings
More informationBANA 7046 Data Mining I Lecture 6. Other Data Mining Algorithms 1
BANA 7046 Data Mining I Lecture 6. Other Data Mining Algorithms 1 Shaobo Li University of Cincinnati 1 Partially based on Hastie, et al. (2009) ESL, and James, et al. (2013) ISLR Data Mining I Lecture
More informationAlgorithms for Classification: The Basic Methods
Algorithms for Classification: The Basic Methods Outline Simplicity first: 1R Naïve Bayes 2 Classification Task: Given a set of pre-classified examples, build a model or classifier to classify new cases.
More informationLogistic Regression & Neural Networks
Logistic Regression & Neural Networks CMSC 723 / LING 723 / INST 725 Marine Carpuat Slides credit: Graham Neubig, Jacob Eisenstein Logistic Regression Perceptron & Probabilities What if we want a probability
More informationUnsupervised Learning: Projections
Unsupervised Learning: Projections CMPSCI 689 Fall 2015 Sridhar Mahadevan Lecture 2 Data, Data, Data LIBS spectrum Steel'drum' The Image Classification Challenge: 1,000 object classes 1,431,167 images
More informationPrepositional Phrase Attachment over Word Embedding Products
Prepositional Phrase Attachment over Word Embedding Products Pranava Madhyastha (1), Xavier Carreras (2), Ariadna Quattoni (2) (1) University of Sheffield (2) Naver Labs Europe Prepositional Phrases I
More informationLecture 3 Classification, Logistic Regression
Lecture 3 Classification, Logistic Regression Fredrik Lindsten Division of Systems and Control Department of Information Technology Uppsala University. Email: fredrik.lindsten@it.uu.se F. Lindsten Summary
More informationLars Schmidt-Thieme, Information Systems and Machine Learning Lab (ISMLL), University of Hildesheim, Germany
Syllabus Fri. 21.10. (1) 0. Introduction A. Supervised Learning: Linear Models & Fundamentals Fri. 27.10. (2) A.1 Linear Regression Fri. 3.11. (3) A.2 Linear Classification Fri. 10.11. (4) A.3 Regularization
More informationCS 540: Machine Learning Lecture 1: Introduction
CS 540: Machine Learning Lecture 1: Introduction AD January 2008 AD () January 2008 1 / 41 Acknowledgments Thanks to Nando de Freitas Kevin Murphy AD () January 2008 2 / 41 Administrivia & Announcement
More informationMachine Learning for natural language processing
Machine Learning for natural language processing Classification: Naive Bayes Laura Kallmeyer Heinrich-Heine-Universität Düsseldorf Summer 2016 1 / 20 Introduction Classification = supervised method for
More informationLearning with multiple models. Boosting.
CS 2750 Machine Learning Lecture 21 Learning with multiple models. Boosting. Milos Hauskrecht milos@cs.pitt.edu 5329 Sennott Square Learning with multiple models: Approach 2 Approach 2: use multiple models
More informationSecurity Analytics. Topic 6: Perceptron and Support Vector Machine
Security Analytics Topic 6: Perceptron and Support Vector Machine Purdue University Prof. Ninghui Li Based on slides by Prof. Jenifer Neville and Chris Clifton Readings Principle of Data Mining Chapter
More informationA Randomized Approach for Crowdsourcing in the Presence of Multiple Views
A Randomized Approach for Crowdsourcing in the Presence of Multiple Views Presenter: Yao Zhou joint work with: Jingrui He - 1 - Roadmap Motivation Proposed framework: M2VW Experimental results Conclusion
More informationLecture 7: Kernels for Classification and Regression
Lecture 7: Kernels for Classification and Regression CS 194-10, Fall 2011 Laurent El Ghaoui EECS Department UC Berkeley September 15, 2011 Outline Outline A linear regression problem Linear auto-regressive
More informationMachine Learning Practice Page 2 of 2 10/28/13
Machine Learning 10-701 Practice Page 2 of 2 10/28/13 1. True or False Please give an explanation for your answer, this is worth 1 pt/question. (a) (2 points) No classifier can do better than a naive Bayes
More informationMachine Learning for natural language processing
Machine Learning for natural language processing Classification: Maximum Entropy Models Laura Kallmeyer Heinrich-Heine-Universität Düsseldorf Summer 2016 1 / 24 Introduction Classification = supervised
More informationDeep Learning for NLP
Deep Learning for NLP CS224N Christopher Manning (Many slides borrowed from ACL 2012/NAACL 2013 Tutorials by me, Richard Socher and Yoshua Bengio) Machine Learning and NLP NER WordNet Usually machine learning
More informationModeling Data with Linear Combinations of Basis Functions. Read Chapter 3 in the text by Bishop
Modeling Data with Linear Combinations of Basis Functions Read Chapter 3 in the text by Bishop A Type of Supervised Learning Problem We want to model data (x 1, t 1 ),..., (x N, t N ), where x i is a vector
More informationInstructions for NLP Practical (Units of Assessment) SVM-based Sentiment Detection of Reviews (Part 2)
Instructions for NLP Practical (Units of Assessment) SVM-based Sentiment Detection of Reviews (Part 2) Simone Teufel (Lead demonstrator Guy Aglionby) sht25@cl.cam.ac.uk; ga384@cl.cam.ac.uk This is the
More informationSupport Vector Machines for Classification: A Statistical Portrait
Support Vector Machines for Classification: A Statistical Portrait Yoonkyung Lee Department of Statistics The Ohio State University May 27, 2011 The Spring Conference of Korean Statistical Society KAIST,
More informationFast classification using sparsely active spiking networks. Hesham Mostafa Institute of neural computation, UCSD
Fast classification using sparsely active spiking networks Hesham Mostafa Institute of neural computation, UCSD Artificial networks vs. spiking networks backpropagation output layer Multi-layer networks
More informationSupport Vector Machine & Its Applications
Support Vector Machine & Its Applications A portion (1/3) of the slides are taken from Prof. Andrew Moore s SVM tutorial at http://www.cs.cmu.edu/~awm/tutorials Mingyue Tan The University of British Columbia
More information11/3/15. Deep Learning for NLP. Deep Learning and its Architectures. What is Deep Learning? Advantages of Deep Learning (Part 1)
11/3/15 Machine Learning and NLP Deep Learning for NLP Usually machine learning works well because of human-designed representations and input features CS224N WordNet SRL Parser Machine learning becomes
More informationarxiv: v3 [stat.ml] 1 Nov 2015
Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding arxiv:1504.01255v3 [stat.ml] 1 Nov 2015 Rie Johnson RJ Research Consulting Tarrytown, NY, USA riejohnson@gmail.com
More informationFrom perceptrons to word embeddings. Simon Šuster University of Groningen
From perceptrons to word embeddings Simon Šuster University of Groningen Outline A basic computational unit Weighting some input to produce an output: classification Perceptron Classify tweets Written
More informationStat 406: Algorithms for classification and prediction. Lecture 1: Introduction. Kevin Murphy. Mon 7 January,
1 Stat 406: Algorithms for classification and prediction Lecture 1: Introduction Kevin Murphy Mon 7 January, 2008 1 1 Slides last updated on January 7, 2008 Outline 2 Administrivia Some basic definitions.
More informationData Mining & Machine Learning
Data Mining & Machine Learning CS57300 Purdue University March 1, 2018 1 Recap of Last Class (Model Search) Forward and Backward passes 2 Feedforward Neural Networks Neural Networks: Architectures 2-layer
More informationa) b) (Natural Language Processing; NLP) (Deep Learning) Bag of words White House RGB [1] IBM
c 1. (Natural Language Processing; NLP) (Deep Learning) RGB IBM 135 8511 5 6 52 yutat@jp.ibm.com a) b) 2. 1 0 2 1 Bag of words White House 2 [1] 2015 4 Copyright c by ORSJ. Unauthorized reproduction of
More informationMicroarray Data Analysis: Discovery
Microarray Data Analysis: Discovery Lecture 5 Classification Classification vs. Clustering Classification: Goal: Placing objects (e.g. genes) into meaningful classes Supervised Clustering: Goal: Discover
More information1 Inference in Dirichlet Mixture Models Introduction Problem Statement Dirichlet Process Mixtures... 3
Contents 1 Inference in Dirichlet Mixture Models 2 1.1 Introduction....................................... 2 1.2 Problem Statement................................... 2 1.3 Dirichlet Process Mixtures...............................
More informationClassification 2: Linear discriminant analysis (continued); logistic regression
Classification 2: Linear discriminant analysis (continued); logistic regression Ryan Tibshirani Data Mining: 36-462/36-662 April 4 2013 Optional reading: ISL 4.4, ESL 4.3; ISL 4.3, ESL 4.4 1 Reminder:
More informationGenerative Learning. INFO-4604, Applied Machine Learning University of Colorado Boulder. November 29, 2018 Prof. Michael Paul
Generative Learning INFO-4604, Applied Machine Learning University of Colorado Boulder November 29, 2018 Prof. Michael Paul Generative vs Discriminative The classification algorithms we have seen so far
More informationCS534 Machine Learning - Spring Final Exam
CS534 Machine Learning - Spring 2013 Final Exam Name: You have 110 minutes. There are 6 questions (8 pages including cover page). If you get stuck on one question, move on to others and come back to the
More informationText Mining. Dr. Yanjun Li. Associate Professor. Department of Computer and Information Sciences Fordham University
Text Mining Dr. Yanjun Li Associate Professor Department of Computer and Information Sciences Fordham University Outline Introduction: Data Mining Part One: Text Mining Part Two: Preprocessing Text Data
More informationHidden Markov Models
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Hidden Markov Models Matt Gormley Lecture 19 Nov. 5, 2018 1 Reminders Homework
More informationMachine Learning. Classification, Discriminative learning. Marc Toussaint University of Stuttgart Summer 2015
Machine Learning Classification, Discriminative learning Structured output, structured input, discriminative function, joint input-output features, Likelihood Maximization, Logistic regression, binary
More informationCollaborative Filtering. Radek Pelánek
Collaborative Filtering Radek Pelánek 2017 Notes on Lecture the most technical lecture of the course includes some scary looking math, but typically with intuitive interpretation use of standard machine
More informationMaking Deep Learning Understandable for Analyzing Sequential Data about Gene Regulation
Making Deep Learning Understandable for Analyzing Sequential Data about Gene Regulation Dr. Yanjun Qi Department of Computer Science University of Virginia Tutorial @ ACM BCB-2018 8/29/18 Yanjun Qi / UVA
More informationMidterm Review CS 6375: Machine Learning. Vibhav Gogate The University of Texas at Dallas
Midterm Review CS 6375: Machine Learning Vibhav Gogate The University of Texas at Dallas Machine Learning Supervised Learning Unsupervised Learning Reinforcement Learning Parametric Y Continuous Non-parametric
More informationLearning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text
Learning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text Yi Zhang Machine Learning Department Carnegie Mellon University yizhang1@cs.cmu.edu Jeff Schneider The Robotics Institute
More information