Advanced topics in RSA. Nikolaus Kriegeskorte MRC Cognition and Brain Sciences Unit Cambridge, UK

Size: px
Start display at page:

Download "Advanced topics in RSA. Nikolaus Kriegeskorte MRC Cognition and Brain Sciences Unit Cambridge, UK"

Transcription

1 Advanced topics in RSA Nikolaus Kriegeskorte MRC Cognition and Brain Sciences Unit Cambridge, UK

2 Advanced topics menu How does the noise ceiling work? Why is Kendall s tau a often needed to compare RDMs? How can we weight model features to explain brain RDMs? What s the difference between dissimilarity, distance, and metric?

3 How does the noise ceiling work?

4 Correlation distance Euclidean distance 2 (for normalised patterns) d d 2 = (1 r) r 2 = 1 2r + r r 2 = 2(1 r) 1 r 1 r cos α = r Nili et al. 2014

5 highest accuracy any model can achieve accuracy of human IT dissimilarity matrix prediction [group-average rank correlation] other subjects average as model SE (stimulus bootstrap) accuracy above chance p<0.001 (subjects and stimuli as fixed effects) convolutional fully connected SVM discriminants Khaligh-Razavi & Kriegeskorte (2014), Nili et al (RSA Toolbox) weighted combination of fully connected layers and SVM discriminants

6 distance 2 Estimating the noise ceiling subject 2 subject 1 true model group mean subject 3 The group-mean RDM minimises the sum of squared Euclidean distances to singlesubject RDMs. For rank RDMs, the groupmean RDM therefore minimises the sum of correlation distances (thus maximising the average correlation). The average correlation to the group-mean of rank RDMs, thus provides a precise and hard upper bound on the average Spearman correlation any model can achieve. distance 1 Nili et al upper bound For Kendall s tau a, an iterative procedure is needed to find the hard upper bound.

7 distance 2 distance 2 Estimating the noise ceiling subject 2 subject 1 true model group mean subject 3 subject 1 (held out) leave-one-out group mean true model distance 1 Nili et al upper bound distance 1 lower bound

8 Why is Kendall s tau a often needed to compare RDMs? Kendall s tau a is needed when testing categorical models that predict tied dissimilarities.

9 General correlation coefficient difference matrix Pearson Spearman Kendall Kendall 1944

10 True model can lose to simplified step model (according to most correlation coefficients) Nili et al. 2014

11 True model can lose to simplified step model (according to most correlation coefficients) Nili et al simulated data real data

12 True model can lose to simplified step model (according to most correlation coefficients) Nili et al simulated data real data

13 ranks values True model can lose to simplified step model (according to most correlation coefficients) true model noisy data step model data points data points

14 ranks values True model can lose to simplified step model (according to most correlation coefficients) true model noisy data step model data points Pearson, tau-a data points

15 Kendall s tau a chooses the true model over a simplified model (which predicts ties in hard cases) more frequently than Pearson r, Spearman r, tau b and tau c true model always preferred proportion of cases in which the true model was preferred true model never preferred noise level in the data

16 Conclusions Rank correlation can be useful for comparing RDMs when measurement errors might distort a simple linear relationship. When categorical models (predicting tied ranks) are used, Kendall s tau a is an appropriate rank correlation coefficient. Kendall s tau b & c, Spearman correlation, and even Pearson correlation all prefer models that predict ties for difficult comparisons to the true model.

17 How can we weight model features to explain brain RDMs?

18 highest accuracy any model can achieve accuracy of human IT dissimilarity matrix prediction [group-average of Kendall s a ] other subjects average as model SE (stimulus bootstrap) accuracy above chance p<0.001 (subjects and stimuli as fixed effects) convolutional fully connected SVM discriminants Khaligh-Razavi & Kriegeskorte (2014), Nili et al (RSA Toolbox) weighted combination of fully connected layers and SVM discriminants

19 Khaligh-Razavi & Kriegeskorte (2014)

20 Khaligh-Razavi & Kriegeskorte (2014) Representational feature weighting with non-negative least-squares f 1 f 2... f k model RDM w 1 f 1 w 2 f 2... w k f k weighted-model RDM

21 predicted distance Representational feature weighting with non-negative least-squares n d i,j 2 = [wk f k i w k f k j ] 2 k=1 n = w k 2 [f k i f k j ] 2 k=1 weight k stimuli i, j model feature k The squared distance RDM of weighted model features equals a weighted sum of single-feature RDMs. w 1 2 feature-1 RDM +w 2 2 feature-2 RDM... +w k 2 feature-k RDM = weighted-model RDM w = arg min w R +n d i,j 2 d i,j 2 2 i j = arg min d 2 w 2 w R +n k RDM k i j n k=1 i,j 2 Khaligh-Razavi & Kriegeskorte (2014) w k weight given to model feature k f k (i) model feature k for stimulus i d i,j distance between stimuli i,j w is the weight vector [w 1 w 2... w k ] minimising the squared errors

22 What s the difference between dissimilarity, distance, and metric?

23 Dissimilarity measures d(x,y) = d(y,x) LD-t Distances correlation distance squared Euclidean distance Minkowski distance with p < 1 d(x,y) 0 Metrics d(x,y) = 0 x = y d(x,z) d(x,y) + d(y,z) Euclidean distance Mahalanobis distance Minkowski distance with p 1

Introduction to representational similarity analysis

Introduction to representational similarity analysis Introduction to representational similarity analysis Nikolaus Kriegeskorte MRC Cognition and Brain Sciences Unit Cambridge RSA Workshop, 16-17 February 2015 a c t i v i t y d i s s i m i l a r i t y Representational

More information

Representational similarity analysis. Nikolaus Kriegeskorte MRC Cognition and Brain Sciences Unit Cambridge, UK

Representational similarity analysis. Nikolaus Kriegeskorte MRC Cognition and Brain Sciences Unit Cambridge, UK Representational similarity analysis Nikolaus Kriegeskorte MRC Cognition and Brain Sciences Unit Cambridge, UK a c t i v i t y d i s s i m i l a r i t y Representational similarity analysis stimulus (e.g.

More information

Estimating representational dissimilarity measures

Estimating representational dissimilarity measures Estimating representational dissimilarity measures lexander Walther MRC Cognition and rain Sciences Unit University of Cambridge Institute of Cognitive Neuroscience University

More information

Session III: New ETSI Model on Wideband Speech and Noise Transmission Quality Phase II. STF Validation results

Session III: New ETSI Model on Wideband Speech and Noise Transmission Quality Phase II. STF Validation results Session III: New ETSI Model on Wideband Speech and Noise Transmission Quality Phase II STF 294 - Validation results ETSI Workshop on Speech and Noise in Wideband Communication Javier Aguiar (University

More information

Unsupervised machine learning

Unsupervised machine learning Chapter 9 Unsupervised machine learning Unsupervised machine learning (a.k.a. cluster analysis) is a set of methods to assign objects into clusters under a predefined distance measure when class labels

More information

Multimedia Retrieval Distance. Egon L. van den Broek

Multimedia Retrieval Distance. Egon L. van den Broek Multimedia Retrieval 2018-1019 Distance Egon L. van den Broek 1 The project: Two perspectives Man Machine or? Objective Subjective 2 The default Default: distance = Euclidean distance This is how it is

More information

Type of data Interval-scaled variables: Binary variables: Nominal, ordinal, and ratio variables: Variables of mixed types: Attribute Types Nominal: Pr

Type of data Interval-scaled variables: Binary variables: Nominal, ordinal, and ratio variables: Variables of mixed types: Attribute Types Nominal: Pr Foundation of Data Mining i Topic: Data CMSC 49D/69D CSEE Department, e t, UMBC Some of the slides used in this presentation are prepared by Jiawei Han and Micheline Kamber Data Data types Quality of data

More information

Understand the difference between symmetric and asymmetric measures

Understand the difference between symmetric and asymmetric measures Chapter 9 Measures of Strength of a Relationship Learning Objectives Understand the strength of association between two variables Explain an association from a table of joint frequencies Understand a proportional

More information

Web Structure Mining Nodes, Links and Influence

Web Structure Mining Nodes, Links and Influence Web Structure Mining Nodes, Links and Influence 1 Outline 1. Importance of nodes 1. Centrality 2. Prestige 3. Page Rank 4. Hubs and Authority 5. Metrics comparison 2. Link analysis 3. Influence model 1.

More information

τ xy N c N d n(n 1) / 2 n +1 y = n 1 12 v n n(n 1) ρ xy Brad Thiessen

τ xy N c N d n(n 1) / 2 n +1 y = n 1 12 v n n(n 1) ρ xy Brad Thiessen Introduction: Effect of Correlation Types on Nonmetric Multidimensional Scaling of ITED Subscore Data Brad Thiessen In a discussion of potential data types that can be used as proximity measures, Coxon

More information

1. Pearson linear correlation calculating testing multiple correlation. 2. Spearman rank correlation calculating testing 3. Other correlation measures

1. Pearson linear correlation calculating testing multiple correlation. 2. Spearman rank correlation calculating testing 3. Other correlation measures STATISTICAL METHODS 1. Introductory lecture 2. Random variables and probability theory 3. Populations and samples 4. Hypotheses testing and parameter estimation 5. Most widely used statistical tests I.

More information

Data Mining: Data. Lecture Notes for Chapter 2. Introduction to Data Mining

Data Mining: Data. Lecture Notes for Chapter 2. Introduction to Data Mining Data Mining: Data Lecture Notes for Chapter 2 Introduction to Data Mining by Tan, Steinbach, Kumar Similarity and Dissimilarity Similarity Numerical measure of how alike two data objects are. Is higher

More information

NON-PARAMETRIC STATISTICS * (http://www.statsoft.com)

NON-PARAMETRIC STATISTICS * (http://www.statsoft.com) NON-PARAMETRIC STATISTICS * (http://www.statsoft.com) 1. GENERAL PURPOSE 1.1 Brief review of the idea of significance testing To understand the idea of non-parametric statistics (the term non-parametric

More information

Linking non-binned spike train kernels to several existing spike train metrics

Linking non-binned spike train kernels to several existing spike train metrics Linking non-binned spike train kernels to several existing spike train metrics Benjamin Schrauwen Jan Van Campenhout ELIS, Ghent University, Belgium Benjamin.Schrauwen@UGent.be Abstract. This work presents

More information

Data Mining: Data. Lecture Notes for Chapter 2 Slides by Tan, Steinbach, Kumar adapted by Michael Hahsler

Data Mining: Data. Lecture Notes for Chapter 2 Slides by Tan, Steinbach, Kumar adapted by Michael Hahsler Data Mining: Data Lecture Notes for Chapter 2 Slides by Tan, Steinbach, Kumar adapted by Michael Hahsler Look for accompanying R code on the course web site. 1 Topics Attributes/Features Types of Data

More information

M3: Multiple View Geometry

M3: Multiple View Geometry M3: Multiple View Geometry L18: Projective Structure from Motion: Iterative Algorithm based on Factorization Based on Sections 13.4 C. V. Jawahar jawahar-at-iiit.net Mar 2005: 1 Review: Reconstruction

More information

The Gerber Statistic: A Robust Measure of Correlation

The Gerber Statistic: A Robust Measure of Correlation The Gerber Statistic: A Robust Measure of Correlation Sander Gerber Babak Javid Harry Markowitz Paul Sargen David Starer February 21, 2019 Abstract We introduce the Gerber statistic, a robust measure of

More information

Textbook Examples of. SPSS Procedure

Textbook Examples of. SPSS Procedure Textbook s of IBM SPSS Procedures Each SPSS procedure listed below has its own section in the textbook. These sections include a purpose statement that describes the statistical test, identification of

More information

Types of Statistical Tests DR. MIKE MARRAPODI

Types of Statistical Tests DR. MIKE MARRAPODI Types of Statistical Tests DR. MIKE MARRAPODI Tests t tests ANOVA Correlation Regression Multivariate Techniques Non-parametric t tests One sample t test Independent t test Paired sample t test One sample

More information

Lecture: Face Recognition

Lecture: Face Recognition Lecture: Face Recognition Juan Carlos Niebles and Ranjay Krishna Stanford Vision and Learning Lab Lecture 12-1 What we will learn today Introduction to face recognition The Eigenfaces Algorithm Linear

More information

Unit 14: Nonparametric Statistical Methods

Unit 14: Nonparametric Statistical Methods Unit 14: Nonparametric Statistical Methods Statistics 571: Statistical Methods Ramón V. León 8/8/2003 Unit 14 - Stat 571 - Ramón V. León 1 Introductory Remarks Most methods studied so far have been based

More information

Chapter 16: Correlation

Chapter 16: Correlation Chapter 16: Correlation Correlations: Measuring and Describing Relationships A correlation is a statistical method used to measure and describe the relationship between two variables. A relationship exists

More information

Tau is a relatively new measure of correlation and is more appropriate

Tau is a relatively new measure of correlation and is more appropriate Memo on the use Bob Yieiss April 16, 1952 of Kendall's tau S31 Tau is a relatively new measure of correlation and is more appropriate for much social science work than is either the Spearman rank order

More information

A Bayesian method for reducing bias in neural representational similarity analysis

A Bayesian method for reducing bias in neural representational similarity analysis A Bayesian method for reducing bias in neural representational similarity analysis Ming Bo Cai Princeton Neuroscience Institute Princeton University Princeton, NJ 08544 mcai@princeton.edu Jonathan W. Pillow

More information

Overview of clustering analysis. Yuehua Cui

Overview of clustering analysis. Yuehua Cui Overview of clustering analysis Yuehua Cui Email: cuiy@msu.edu http://www.stt.msu.edu/~cui A data set with clear cluster structure How would you design an algorithm for finding the three clusters in this

More information

Lecture Notes DRE 7007 Mathematics, PhD

Lecture Notes DRE 7007 Mathematics, PhD Eivind Eriksen Lecture Notes DRE 7007 Mathematics, PhD August 21, 2012 BI Norwegian Business School Contents 1 Basic Notions.................................................. 1 1.1 Sets......................................................

More information

Notes 21: Scatterplots, Association, Causation

Notes 21: Scatterplots, Association, Causation STA 6166 Fall 27 Web-based Course Notes 21, page 1 Notes 21: Scatterplots, Association, Causation We used two-way tables and segmented bar charts to examine the relationship between two categorical variables

More information

Statistical comparisons for the topological equivalence of proximity measures

Statistical comparisons for the topological equivalence of proximity measures Statistical comparisons for the topological equivalence of proximity measures Rafik Abdesselam and Djamel Abdelkader Zighed 2 ERIC Laboratory, University of Lyon 2 Campus Porte des Alpes, 695 Bron, France

More information

Descriptive Data Summarization

Descriptive Data Summarization Descriptive Data Summarization Descriptive data summarization gives the general characteristics of the data and identify the presence of noise or outliers, which is useful for successful data cleaning

More information

A Balanced Comparison of Object Invariances in Monkey IT Neurons

A Balanced Comparison of Object Invariances in Monkey IT Neurons New Research Sensory and Motor Systems A Balanced Comparison of Object Invariances in Monkey IT Neurons N. Apurva Ratan Murty and Sripati P. Arun DOI:http://dx.doi.org/1.1523/ENEURO.333-16.217 Centre for

More information

Visual matching: distance measures

Visual matching: distance measures Visual matching: distance measures Metric and non-metric distances: what distance to use It is generally assumed that visual data may be thought of as vectors (e.g. histograms) that can be compared for

More information

Centrality Measures. Leonid E. Zhukov

Centrality Measures. Leonid E. Zhukov Centrality Measures Leonid E. Zhukov School of Data Analysis and Artificial Intelligence Department of Computer Science National Research University Higher School of Economics Network Science Leonid E.

More information

Data files for today. CourseEvalua2on2.sav pontokprediktorok.sav Happiness.sav Ca;erplot.sav

Data files for today. CourseEvalua2on2.sav pontokprediktorok.sav Happiness.sav Ca;erplot.sav Correlation Data files for today CourseEvalua2on2.sav pontokprediktorok.sav Happiness.sav Ca;erplot.sav Defining Correlation Co-variation or co-relation between two variables These variables change together

More information

Centrality Measures. Leonid E. Zhukov

Centrality Measures. Leonid E. Zhukov Centrality Measures Leonid E. Zhukov School of Data Analysis and Artificial Intelligence Department of Computer Science National Research University Higher School of Economics Structural Analysis and Visualization

More information

Association Between Variables Measured at the Ordinal Level

Association Between Variables Measured at the Ordinal Level Last week: Examining associations. Is the association significant? (chi square test) Strength of the association (with at least one variable nominal) maximum difference approach chi/cramer s v/lambda Nature

More information

Concepts & Categorization. Measurement of Similarity

Concepts & Categorization. Measurement of Similarity Concepts & Categorization Measurement of Similarity Geometric approach Featural approach both are vector representations Vector-representation for words Words represented as vectors of feature values Similar

More information

Machine Learning on temporal data

Machine Learning on temporal data Machine Learning on temporal data Learning Dissimilarities on Time Series Ahlame Douzal (Ahlame.Douzal@imag.fr) AMA, LIG, Université Joseph Fourier Master 2R - MOSIG (2011) Plan Time series structure and

More information

Semi Supervised Distance Metric Learning

Semi Supervised Distance Metric Learning Semi Supervised Distance Metric Learning wliu@ee.columbia.edu Outline Background Related Work Learning Framework Collaborative Image Retrieval Future Research Background Euclidean distance d( x, x ) =

More information

Uwe Aickelin and Qi Chen, School of Computer Science and IT, University of Nottingham, NG8 1BB, UK {uxa,

Uwe Aickelin and Qi Chen, School of Computer Science and IT, University of Nottingham, NG8 1BB, UK {uxa, On Affinity Measures for Artificial Immune System Movie Recommenders Proceedings RASC-2004, The 5th International Conference on: Recent Advances in Soft Computing, Nottingham, UK, 2004. Uwe Aickelin and

More information

Distance Metric Learning

Distance Metric Learning Distance Metric Learning Technical University of Munich Department of Informatics Computer Vision Group November 11, 2016 M.Sc. John Chiotellis: Distance Metric Learning 1 / 36 Outline Computer Vision

More information

COS 429: COMPUTER VISON Face Recognition

COS 429: COMPUTER VISON Face Recognition COS 429: COMPUTER VISON Face Recognition Intro to recognition PCA and Eigenfaces LDA and Fisherfaces Face detection: Viola & Jones (Optional) generic object models for faces: the Constellation Model Reading:

More information

Practical Bioinformatics

Practical Bioinformatics 5/15/2015 Gotchas Indentation matters Clustering exercises Visualizing the distance matrix Loading and re-loading your functions # Use import the f i r s t time you l o a d a module # ( And keep u s i

More information

Chapter 20 d-metal complexes: electronic structures and properties

Chapter 20 d-metal complexes: electronic structures and properties CHEM 511 Chapter 20 page 1 of 21 Chapter 20 d-metal complexes: electronic structures and properties Recall the shape of the d-orbitals... Electronic structure Crystal Field Theory: an electrostatic approach

More information

Measuring relationships among multiple responses

Measuring relationships among multiple responses Measuring relationships among multiple responses Linear association (correlation, relatedness, shared information) between pair-wise responses is an important property used in almost all multivariate analyses.

More information

University of Florida CISE department Gator Engineering. Clustering Part 1

University of Florida CISE department Gator Engineering. Clustering Part 1 Clustering Part 1 Dr. Sanjay Ranka Professor Computer and Information Science and Engineering University of Florida, Gainesville What is Cluster Analysis? Finding groups of objects such that the objects

More information

Some topics in analysis related to Banach algebras, 2

Some topics in analysis related to Banach algebras, 2 Some topics in analysis related to Banach algebras, 2 Stephen Semmes Rice University... Abstract Contents I Preliminaries 3 1 A few basic inequalities 3 2 q-semimetrics 4 3 q-absolute value functions 7

More information

1 Basic Concept and Similarity Measures

1 Basic Concept and Similarity Measures THE UNIVERSITY OF CHICAGO Graduate School of Business Business 41912, Spring Quarter 2016, Mr. Ruey S. Tsay Lecture 10: Cluster Analysis and Multidimensional Scaling 1 Basic Concept and Similarity Measures

More information

Inter-Rater Agreement

Inter-Rater Agreement Engineering Statistics (EGC 630) Dec., 008 http://core.ecu.edu/psyc/wuenschk/spss.htm Degree of agreement/disagreement among raters Inter-Rater Agreement Psychologists commonly measure various characteristics

More information

DATA MINING LECTURE 8. Dimensionality Reduction PCA -- SVD

DATA MINING LECTURE 8. Dimensionality Reduction PCA -- SVD DATA MINING LECTURE 8 Dimensionality Reduction PCA -- SVD The curse of dimensionality Real data usually have thousands, or millions of dimensions E.g., web documents, where the dimensionality is the vocabulary

More information

Introduction to inferential statistics. Alissa Melinger IGK summer school 2006 Edinburgh

Introduction to inferential statistics. Alissa Melinger IGK summer school 2006 Edinburgh Introduction to inferential statistics Alissa Melinger IGK summer school 2006 Edinburgh Short description Prereqs: I assume no prior knowledge of stats This half day tutorial on statistical analysis will

More information

Stat 542: Item Response Theory Modeling Using The Extended Rank Likelihood

Stat 542: Item Response Theory Modeling Using The Extended Rank Likelihood Stat 542: Item Response Theory Modeling Using The Extended Rank Likelihood Jonathan Gruhl March 18, 2010 1 Introduction Researchers commonly apply item response theory (IRT) models to binary and ordinal

More information

Principles of Pattern Recognition. C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata

Principles of Pattern Recognition. C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata Principles of Pattern Recognition C. A. Murthy Machine Intelligence Unit Indian Statistical Institute Kolkata e-mail: murthy@isical.ac.in Pattern Recognition Measurement Space > Feature Space >Decision

More information

Unsupervised learning: beyond simple clustering and PCA

Unsupervised learning: beyond simple clustering and PCA Unsupervised learning: beyond simple clustering and PCA Liza Rebrova Self organizing maps (SOM) Goal: approximate data points in R p by a low-dimensional manifold Unlike PCA, the manifold does not have

More information

Ad Placement Strategies

Ad Placement Strategies Case Study : Estimating Click Probabilities Intro Logistic Regression Gradient Descent + SGD AdaGrad Machine Learning for Big Data CSE547/STAT548, University of Washington Emily Fox January 7 th, 04 Ad

More information

Clustering Lecture 1: Basics. Jing Gao SUNY Buffalo

Clustering Lecture 1: Basics. Jing Gao SUNY Buffalo Clustering Lecture 1: Basics Jing Gao SUNY Buffalo 1 Outline Basics Motivation, definition, evaluation Methods Partitional Hierarchical Density-based Mixture model Spectral methods Advanced topics Clustering

More information

Distances & Similarities

Distances & Similarities Introduction to Data Mining Distances & Similarities CPSC/AMTH 445a/545a Guy Wolf guy.wolf@yale.edu Yale University Fall 2016 CPSC 445 (Guy Wolf) Distances & Similarities Yale - Fall 2016 1 / 22 Outline

More information

UNIT 4 RANK CORRELATION (Rho AND KENDALL RANK CORRELATION

UNIT 4 RANK CORRELATION (Rho AND KENDALL RANK CORRELATION UNIT 4 RANK CORRELATION (Rho AND KENDALL RANK CORRELATION Structure 4.0 Introduction 4.1 Objectives 4. Rank-Order s 4..1 Rank-order data 4.. Assumptions Underlying Pearson s r are Not Satisfied 4.3 Spearman

More information

Subject CS1 Actuarial Statistics 1 Core Principles

Subject CS1 Actuarial Statistics 1 Core Principles Institute of Actuaries of India Subject CS1 Actuarial Statistics 1 Core Principles For 2019 Examinations Aim The aim of the Actuarial Statistics 1 subject is to provide a grounding in mathematical and

More information

Linear vs Non-linear classifier. CS789: Machine Learning and Neural Network. Introduction

Linear vs Non-linear classifier. CS789: Machine Learning and Neural Network. Introduction Linear vs Non-linear classifier CS789: Machine Learning and Neural Network Support Vector Machine Jakramate Bootkrajang Department of Computer Science Chiang Mai University Linear classifier is in the

More information

Computing Trusted Authority Scores in Peer-to-Peer Web Search Networks

Computing Trusted Authority Scores in Peer-to-Peer Web Search Networks Computing Trusted Authority Scores in Peer-to-Peer Web Search Networks Josiane Xavier Parreira, Debora Donato, Carlos Castillo, Gerhard Weikum Max-Planck Institute for Informatics Yahoo! Research May 8,

More information

Robust Sound Event Detection in Continuous Audio Environments

Robust Sound Event Detection in Continuous Audio Environments Robust Sound Event Detection in Continuous Audio Environments Haomin Zhang 1, Ian McLoughlin 2,1, Yan Song 1 1 National Engineering Laboratory of Speech and Language Information Processing The University

More information

Bivariate Paired Numerical Data

Bivariate Paired Numerical Data Bivariate Paired Numerical Data Pearson s correlation, Spearman s ρ and Kendall s τ, tests of independence University of California, San Diego Instructor: Ery Arias-Castro http://math.ucsd.edu/~eariasca/teaching.html

More information

statistical methods for tailoring seasonal climate forecasts Andrew W. Robertson, IRI

statistical methods for tailoring seasonal climate forecasts Andrew W. Robertson, IRI statistical methods for tailoring seasonal climate forecasts Andrew W. Robertson, IRI tailored seasonal forecasts why do we make probabilistic forecasts? to reduce our uncertainty about the (unknown) future

More information

Chapter 9: Association Between Variables Measured at the Ordinal Level

Chapter 9: Association Between Variables Measured at the Ordinal Level Chapter 9: Association Between Variables Measured at the Ordinal Level After this week s class: SHOULD BE ABLE TO COMPLETE ALL APLIA ASSIGNMENTS DUE END OF THIS WEEK: APLIA ASSIGNMENTS 5-7 DUE: Friday

More information

ECE521 week 3: 23/26 January 2017

ECE521 week 3: 23/26 January 2017 ECE521 week 3: 23/26 January 2017 Outline Probabilistic interpretation of linear regression - Maximum likelihood estimation (MLE) - Maximum a posteriori (MAP) estimation Bias-variance trade-off Linear

More information

Cross Entropy. Owen Jones, Cardiff University. Cross Entropy. CE for rare events. CE for disc opt. TSP example. A new setting. Necessary.

Cross Entropy. Owen Jones, Cardiff University. Cross Entropy. CE for rare events. CE for disc opt. TSP example. A new setting. Necessary. Owen Jones, Cardiff University The Cross-Entropy (CE) method started as an adaptive importance sampling scheme for estimating rare event probabilities (Rubinstein, 1997), before being successfully applied

More information

N Utilization of Nursing Research in Advanced Practice, Summer 2008

N Utilization of Nursing Research in Advanced Practice, Summer 2008 University of Michigan Deep Blue deepblue.lib.umich.edu 2008-07 536 - Utilization of ursing Research in Advanced Practice, Summer 2008 Tzeng, Huey-Ming Tzeng, H. (2008, ctober 1). Utilization of ursing

More information

Notion of Distance. Metric Distance Binary Vector Distances Tangent Distance

Notion of Distance. Metric Distance Binary Vector Distances Tangent Distance Notion of Distance Metric Distance Binary Vector Distances Tangent Distance Distance Measures Many pattern recognition/data mining techniques are based on similarity measures between objects e.g., nearest-neighbor

More information

Dissimilarity, Quasimetric, Metric

Dissimilarity, Quasimetric, Metric Dissimilarity, Quasimetric, Metric Ehtibar N. Dzhafarov Purdue University and Swedish Collegium for Advanced Study Abstract Dissimilarity is a function that assigns to every pair of stimuli a nonnegative

More information

Clustering. Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein. Some slides adapted from Jacques van Helden

Clustering. Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein. Some slides adapted from Jacques van Helden Clustering Genome 559: Introduction to Statistical and Computational Genomics Elhanan Borenstein Some slides adapted from Jacques van Helden Small vs. large parsimony A quick review Fitch s algorithm:

More information

Correlation & Linear Regression. Slides adopted fromthe Internet

Correlation & Linear Regression. Slides adopted fromthe Internet Correlation & Linear Regression Slides adopted fromthe Internet Roadmap Linear Correlation Spearman s rho correlation Kendall s tau correlation Linear regression Linear correlation Recall: Covariance n

More information

EVALUATING THE REPEATABILITY OF TWO STUDIES OF A LARGE NUMBER OF OBJECTS: MODIFIED KENDALL RANK-ORDER ASSOCIATION TEST

EVALUATING THE REPEATABILITY OF TWO STUDIES OF A LARGE NUMBER OF OBJECTS: MODIFIED KENDALL RANK-ORDER ASSOCIATION TEST EVALUATING THE REPEATABILITY OF TWO STUDIES OF A LARGE NUMBER OF OBJECTS: MODIFIED KENDALL RANK-ORDER ASSOCIATION TEST TIAN ZHENG, SHAW-HWA LO DEPARTMENT OF STATISTICS, COLUMBIA UNIVERSITY Abstract. In

More information

Cognitive semantics and cognitive theories of representation: Session 6: Conceptual spaces

Cognitive semantics and cognitive theories of representation: Session 6: Conceptual spaces Cognitive semantics and cognitive theories of representation: Session 6: Conceptual spaces Martin Takáč Centre for cognitive science DAI FMFI Comenius University in Bratislava Príprava štúdia matematiky

More information

High Dimensional Search Min- Hashing Locality Sensi6ve Hashing

High Dimensional Search Min- Hashing Locality Sensi6ve Hashing High Dimensional Search Min- Hashing Locality Sensi6ve Hashing Debapriyo Majumdar Data Mining Fall 2014 Indian Statistical Institute Kolkata September 8 and 11, 2014 High Support Rules vs Correla6on of

More information

Dependence. MFM Practitioner Module: Risk & Asset Allocation. John Dodson. September 11, Dependence. John Dodson. Outline.

Dependence. MFM Practitioner Module: Risk & Asset Allocation. John Dodson. September 11, Dependence. John Dodson. Outline. MFM Practitioner Module: Risk & Asset Allocation September 11, 2013 Before we define dependence, it is useful to define Random variables X and Y are independent iff For all x, y. In particular, F (X,Y

More information

CHAPTER 14: SUPPLEMENT

CHAPTER 14: SUPPLEMENT CHAPTER 4: SUPPLEMENT OTHER MEASURES OF ASSOCIATION FOR ORDINAL LEVEL VARIABLES: TAU STATISTICS AND SOMERS D. Introduction Gamma ignores all tied pairs of cases. It therefore may exaggerate the actual

More information

Snowflake Logarithmic Metrics for Face Recognition in the Zernike Domain

Snowflake Logarithmic Metrics for Face Recognition in the Zernike Domain Global Journal of Pure and Applied Mathematics. ISSN 973-768 Volume 3, Number 3 (27), pp. 92 939 Research India Publications http://www.ripublication.com/gjpam.htm Snowflake Logarithmic Metrics for Face

More information

Data Mining 4. Cluster Analysis

Data Mining 4. Cluster Analysis Data Mining 4. Cluster Analysis 4.2 Spring 2010 Instructor: Dr. Masoud Yaghini Outline Data Structures Interval-Valued (Numeric) Variables Binary Variables Categorical Variables Ordinal Variables Variables

More information

Variational Methods in Bayesian Deconvolution

Variational Methods in Bayesian Deconvolution PHYSTAT, SLAC, Stanford, California, September 8-, Variational Methods in Bayesian Deconvolution K. Zarb Adami Cavendish Laboratory, University of Cambridge, UK This paper gives an introduction to the

More information

Similarity and Dissimilarity

Similarity and Dissimilarity 1//015 Similarity and Dissimilarity COMP 465 Data Mining Similarity of Data Data Preprocessing Slides Adapted From : Jiawei Han, Micheline Kamber & Jian Pei Data Mining: Concepts and Techniques, 3 rd ed.

More information

CS-E4830 Kernel Methods in Machine Learning

CS-E4830 Kernel Methods in Machine Learning CS-E4830 Kernel Methods in Machine Learning Lecture 5: Multi-class and preference learning Juho Rousu 11. October, 2017 Juho Rousu 11. October, 2017 1 / 37 Agenda from now on: This week s theme: going

More information

proximity similarity dissimilarity distance Proximity Measures:

proximity similarity dissimilarity distance Proximity Measures: Similarity Measures Similarity and dissimilarity are important because they are used by a number of data mining techniques, such as clustering nearest neighbor classification and anomaly detection. The

More information

RADIO SYSTEMS ETIN15. Lecture no: Equalization. Ove Edfors, Department of Electrical and Information Technology

RADIO SYSTEMS ETIN15. Lecture no: Equalization. Ove Edfors, Department of Electrical and Information Technology RADIO SYSTEMS ETIN15 Lecture no: 8 Equalization Ove Edfors, Department of Electrical and Information Technology Ove.Edfors@eit.lth.se Contents Inter-symbol interference Linear equalizers Decision-feedback

More information

Lab 12: Structured Prediction

Lab 12: Structured Prediction December 4, 2014 Lecture plan structured perceptron application: confused messages application: dependency parsing structured SVM Class review: from modelization to classification What does learning mean?

More information

RETRIEVAL MODELS. Dr. Gjergji Kasneci Introduction to Information Retrieval WS

RETRIEVAL MODELS. Dr. Gjergji Kasneci Introduction to Information Retrieval WS RETRIEVAL MODELS Dr. Gjergji Kasneci Introduction to Information Retrieval WS 2012-13 1 Outline Intro Basics of probability and information theory Retrieval models Boolean model Vector space model Probabilistic

More information

18.6 Regression and Classification with Linear Models

18.6 Regression and Classification with Linear Models 18.6 Regression and Classification with Linear Models 352 The hypothesis space of linear functions of continuous-valued inputs has been used for hundreds of years A univariate linear function (a straight

More information

New image-quality measure based on wavelets

New image-quality measure based on wavelets Journal of Electronic Imaging 19(1), 118 (Jan Mar 2) New image-quality measure based on wavelets Emil Dumic Sonja Grgic Mislav Grgic University of Zagreb Faculty of Electrical Engineering and Computing

More information

Classification. Team Ravana. Team Members Cliffton Fernandes Nikhil Keswaney

Classification. Team Ravana. Team Members Cliffton Fernandes Nikhil Keswaney Email Classification Team Ravana Team Members Cliffton Fernandes Nikhil Keswaney Hello! Cliffton Fernandes MS-CS Nikhil Keswaney MS-CS 2 Topic Area Email Classification Spam: Unsolicited Junk Mail Ham

More information

Cheng Soon Ong & Christian Walder. Canberra February June 2018

Cheng Soon Ong & Christian Walder. Canberra February June 2018 Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 218 Outlines Overview Introduction Linear Algebra Probability Linear Regression 1

More information

EEL 851: Biometrics. An Overview of Statistical Pattern Recognition EEL 851 1

EEL 851: Biometrics. An Overview of Statistical Pattern Recognition EEL 851 1 EEL 851: Biometrics An Overview of Statistical Pattern Recognition EEL 851 1 Outline Introduction Pattern Feature Noise Example Problem Analysis Segmentation Feature Extraction Classification Design Cycle

More information

Convergence rate of SGD

Convergence rate of SGD Convergence rate of SGD heorem: (see Nemirovski et al 09 from readings) Let f be a strongly convex stochastic function Assume gradient of f is Lipschitz continuous and bounded hen, for step sizes: he expected

More information

A beginner s guide to analysis on metric spaces

A beginner s guide to analysis on metric spaces arxiv:math/0408024v1 [math.ca] 2 Aug 2004 A beginner s guide to analysis on metric spaces Stephen William Semmes Rice University Houston, Texas Abstract These notes deal with various kinds of distance

More information

Psychometric Theory. Psychology 405: Psychometric Theory. Psychometric Theory: Goals. Psychometric Theory: Goals II. Psychometric Theory: Requirements

Psychometric Theory. Psychology 405: Psychometric Theory. Psychometric Theory: Goals. Psychometric Theory: Goals II. Psychometric Theory: Requirements Psychometric Theory Psychology 405: Psychometric Theory William Revelle Northwestern University Spring, 2003 http://pmc.psych.nwu.edu/revelle/syllabi/405.html The character which shapes our conduct is

More information

Decomposition of Parsimonious Independence Model Using Pearson, Kendall and Spearman s Correlations for Two-Way Contingency Tables

Decomposition of Parsimonious Independence Model Using Pearson, Kendall and Spearman s Correlations for Two-Way Contingency Tables International Journal of Statistics and Probability; Vol. 7 No. 3; May 208 ISSN 927-7032 E-ISSN 927-7040 Published by Canadian Center of Science and Education Decomposition of Parsimonious Independence

More information

Biological Systems Modeling & Simulation. Konstantinos P. Michmizos, PhD

Biological Systems Modeling & Simulation. Konstantinos P. Michmizos, PhD Biological Systems Modeling & Simulation 2 Konstantinos P. Michmizos, PhD June 25, 2012 Previous Lecture Biomedical Signal examples (1-d, 2-d, 3-d, ) Purpose of Signal Analysis Noise Frequency domain (1-d,

More information

Manning & Schuetze, FSNLP (c) 1999,2000

Manning & Schuetze, FSNLP (c) 1999,2000 558 15 Topics in Information Retrieval (15.10) y 4 3 2 1 0 0 1 2 3 4 5 6 7 8 Figure 15.7 An example of linear regression. The line y = 0.25x + 1 is the best least-squares fit for the four points (1,1),

More information

Package HMMcopula. December 1, 2018

Package HMMcopula. December 1, 2018 Type Package Package HMMcopula December 1, 2018 Title Markov Regime Switching Copula Models Estimation and Goodness of Fit Version 1.0.3 Author Mamadou Yamar Thioub , Bouchra

More information

Statistics: revision

Statistics: revision NST 1B Experimental Psychology Statistics practical 5 Statistics: revision Rudolf Cardinal & Mike Aitken 29 / 30 April 2004 Department of Experimental Psychology University of Cambridge Handouts: Answers

More information

Diffusion Tensor Imaging I. Jennifer Campbell

Diffusion Tensor Imaging I. Jennifer Campbell Diffusion Tensor Imaging I Jennifer Campbell Diffusion Imaging Molecular diffusion The diffusion tensor Diffusion weighting in MRI Alternatives to the tensor Overview of applications Diffusion Imaging

More information

Adaptive Gradient Methods AdaGrad / Adam

Adaptive Gradient Methods AdaGrad / Adam Case Study 1: Estimating Click Probabilities Adaptive Gradient Methods AdaGrad / Adam Machine Learning for Big Data CSE547/STAT548, University of Washington Sham Kakade 1 The Problem with GD (and SGD)

More information