SGN (4 cr) Chapter 10

Size: px
Start display at page:

Download "SGN (4 cr) Chapter 10"

Transcription

1 SGN (4 cr) Chapter 10 Feature Selection and Extraction Jussi Tohka & Jari Niemi Department of Signal Processing Tampere University of Technology February 18, 2014 J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

2 Contents of This Lecture 1 Feature Selection 2 Linear Feature Extraction 3 Multidimensional Scaling J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

3 Material Chapter 10 in WebCop: Extra Material About LASSO: Section in HasTibFri:2009 J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

4 What Should You Already Know? Curse of dimensionality A few carefully chosen (selected or extracted) features may lead to a sufficiently small overlap between the class-conditional pdfs a good classifier which is easy to train and use J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

5 Feature Selection and Extraction 1 / 2 Reducing the number of variables either through feature selection or feature extraction can lead to improved classifier performance or greater understanding of data. Especially important when the number of variables is large w.r.t the number of training data (when n p or n < p). J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

6 Feature Selection and Extraction 2 / 2 Feature selection : select a subset of d features of p available measurements (d has to be determined as well). Also termed subset selection or variable selection although some make distinction between variable and feature selection. Feature extraction: Find a transformation from the p measurements to d-dimensional space (usually d < p). Feature selection and (linear) feature extraction may be regarded as transformation method where a set of weights is applied to original measurements. Both approaches require the optimization of some criterion J. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

7 Feature Selection Reasons for Feature Selection Improving the classifier Removing irrelevant data Reducing storage and computational requirements Reducing the cost of future data collection Reducing the classifier complexity for better understanding of the data Feature selection essential in applications where n p arising often in bioinformatics and neuroimaging. Feature selection not necessary for classifiers that employ regularization (e.g. SVMs) J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

8 Feature Selection Example Applications Brain imaging based Alzheimer s conversion prediction. (Moradi et al. Submitted 2014) Task: Try to predict whether a mild cognitive impairment patient develops Alzheimer s disease within 3 years. Data: 184 MRIs of the MCI patients with about voxels (measurements) Feature selection clearly improves the performance of also SVMs by precenting overfitting. Many bioinformatics examples in Chapter 18 of HasTibFri:2009 J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

9 Feature Selection Feature Selection: Theory 4 kinds of features (denoted by X ) 1 Irrelevant: X not necessary at all. 2 Redundant: Defined via Markov Blankets, see pp Weakly relevant:. Feature not always necessary, but may be for certain subsets (of features); X may be necessary. 4 Strongly relevant: The distribution of the class predictor depends on X ; X cannot be removed. A good feature set will include none of the irrelevant features, some of the weakly relevant features and all strongly relevant features. The subset of weakly relevant features is selected based on redundancy. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

10 Feature Selection Computational Complexity From Huttunen, Manninen, Tohka, FCSE 2012 Evaluation of all possible feature subsets not possible even for small p since the number of subsets is 2 p. For example, for p = 408, the number of subsets is (about) Assume further that annual increase in earth s computational power is 57%. If a subset could be evaluated in a single clock cycle, evaluating all the subsets using all the computational power on the earth, the evaluation of all all subsets would take 517 years. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

11 Feature Selection Categorization of Feature Selection Methods Filters - computationally efficient Wrappers - often better performance than with filters Embedded - feature selection is built in the classifier design. Decision trees and LASSO. may be considered as wrappers. Filters Wrappers Images from Kohavi and John AI-1997 J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

12 Feature Selection Evaluation Measures - Filters Independent of the final classier Feature ranking (next slide) Interclass distance (tables 10.2 and 10.3) Probabilistic distance (Kullback-Leibler, table 10.4) Probabilistic dependence J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

13 Feature Selection Filters: Simple Feature Ranking 2-class problem, p-features Data x 1,..., x n1 from ω 1 ; y 1,..., y n2 from ω 2 For each feature i, compute J(i) = (1/n 1) n 1 j=1 x j i (1/n 2 ) n 2 j=1 y j i, σ(i) where σ(i) is the standard deviation of the ith feature Higher the J(i) more important the feature i Select d best features or select the features with J(i) greater then some threshold. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

14 Filters: Relief Feature Selection Some features may become relevant in the context of others For each pattern x i compute K nearest hits (patterns within the same class, {x Hk (i)}) and K nearest misses (patterns within a different class, {x Mk (i)})). Relief criterion: R(j) = n K i=1 k=1 x i j x Mk (i) j n K i=1 k=1 x i j x Hk (i) j J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

15 Feature Selection Filters: Markov Blanket Warning: This slide is mathematically involved M X a subset of the features X that does contain the feature X. Then M X is a Markov Blanket for X if X is conditionally independent of X M X {X } given M X. G a set of features. A feature in G weakly relevant and can be removed if and only if it is weakly relevant and has a Markov blanket in X. Incremental Association Markov Blanket algorithm: 2 phases 1 Growing: identify features that have a strong dependency on a class variable 2 Shrinking: removes redundant variables J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

16 Feature Selection Evaluation Criteria: Wrappers Error rate is the most widely used evaluation criterion with wrappers Evaluation criterion should resemble (or rather, be the same) as the performance criterion for the classifier itself. If error rate is a poor performance criterion then a more suitable criterion should be selected. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

17 Feature Selection Search Algorithms for Wrappers Complete search - branch and bound, often computationally complex and requires a specific monotonicity property of the evaluation criterion Sequential search - features are added (forward search) or removed sequentially (backward search); Modification: floating versions Random search - inject randomness into the search J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

18 Feature Selection Sequential Forward Selection J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

19 Feature Selection Random Search: Simulated Annealing Example J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

20 Feature Selection Embbeded Methods - LASSO J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

21 Nested CV Feature Selection Note that if a performance assessment is required for an embbedded or a wrapper method, it is imperative to use nested cross-validation for the performance estimate, i.e., to use nested CV loops, inner for feature selection and the outer for the performance evaluation. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

22 Feature Selection Stability of Feature Selection Different feature selection algorithms do not necessarily produce the same ranking of the features give the same dataset Even with the same algorithm, considerable variation between the different CV folds possible/probable. High reproducibility of features can be as important as high classification rate There are stability selection algorithms utilizing these ideas. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

23 Linear Feature Extraction Motivation to feature extraction Feature extraction: Find a transformation from the p measurements to d-dimensional space (usually d < p). to reduce the bandwidth of the original data; to improve the classifier; to reduce the redundancy; to recover new meaningful underlying variables or feature to describe the data to produce graphical representations of the data J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

24 Linear Feature Extraction Principal Component Analysis (PCA) 1 / 2 Derive new variables (in decreasing order of importance) that are linear combinations of the original variables and are uncorrelated. Geometrically, PCA is a rotation of axes of the original coordinate system to a new set of orthogonal axes. Axes are ordered in terms of the amount of variation of the original data they account for (importance in the PCA sense). index.html J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

25 Linear Feature Extraction Principal Component Analysis (PCA) 2 / 2 Let [x 1,..., x p ] T = x be the set of original (random) variables Let [y 1,..., y p ] T = y be linear combination of these variables y = A T x The task is to find the matrix A (or some columns of it) 3 distinct widely-used derivations of PCA 1 (Hotelling) Find orthogonal A yielding y i that have stationary values of their variance 2 Find orthogonal A yielding uncorrelated y i 3 (Pearson) Find (iteratively) columns that give minimum squared error between data and their (linear) projections. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

26 PCA Example Linear Feature Extraction Wine data for UCL repository: 13 chemical measurements for three types of wine Class labels are not used in PCA but shown in the figure J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

27 Linear Feature Extraction PCA Derivation (Hotelling, Sketch) Consider the first variable y 1 : y 1 = j a 1j x j. Choose a 1 = [a 11,..., a 1p ] T to maximize the variance of y 1, subject to a = 1. This is a T 1 Σa 1, where Σ is the covariance of x. It can be shown that a 1 must be the eigenvector of Σ with the maximal eigenvalue. a 2 is the eigenvector of Σ with the 2nd largest eigenvalue, a 3 is the eigenvector of Σ with the 3rd largest eigenvalue, and so on. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

28 Linear Feature Extraction PCA - Notes Sum of the variance of k first PCs is k i=1 λ i, where λ i are (ordered) eigenvalues of the covariance matrix Σ. Thus, the percentage of variance accounted for by k first PCs is k i=1 λ i p i=1 λ i. To reduce the dimensionality, the data x 1,..., x n can be transformed y i = A T k x i where A k = [a 1... a k ] T is p k matrix. Selection of a good k not trivial. x i s often de-meaned PCA ignores the class-information J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

29 Linear Feature Extraction Karhunen-Loeve Transform In its most basic form, Karhunen-Loeve transform is identical to PCA Interestingly, Kari Karhunen was a Finnish mathematician and Emanuel Parzen and Leo Breiman were doctoral students of Michel Loeve In pattern recognition, the umbrella term Karhunen-Loeve expansion has a meaning similar to generalized PCA Summary of various transforms under the umbrella term is given in Table 10.7 J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

30 Kernel PCA Linear Feature Extraction Various other generalizations sucu as kernel PCA J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

31 Linear Feature Extraction Independent Component Analysis (ICA) Separates multivariate signal into additive subcomponents by assuming that the subcomponents are non-gaussian signals and that they are all statistically independent from each other. Let x be the (random vector describing the) observations, let s be the vector of (unobservable) sources, and A the mixing matrix so that x = As. ICA tries to find A (and thereby s by maximizing the independence of the components of s. Note the differences between (and similarities) between ICA and PCA; In ICA s is non-gaussian, ICA does not provide (directly) a ranking of sources. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

32 Linear Feature Extraction ICA - Cocktail Party Problem J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

33 Multidimensional Scaling Classical Scaling Analyses of (Euclidean) proximity matrix to produce a representation of data points in a reduced dimension space (representation space) Classical scaling: For n p-dimensional points x 1,..., x p, it is easy to compute n n matrix T of Euclidean distances. Classical scaling solves converse problem: Given distance matrix T, how to determine the coordinates of the points (in dimension e)? Based on the n n dissimilarity matrix D construct T such that T = XX T (X n p matrix of the wanted coordinates). (Easy) Solve X : T symmetric T = UΛU T, where U are the eigenvectors of T and Λ the diagonal eigenvalue matrix. Take X = UΛ (1/2). In reduced dimension only part of the eigenvalues is used in a similar way than in PCA. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

34 Multidimensional Scaling Metric MDS and Ordinal Scaling Metric MDS: Optimize an objective function measuring the discrepancy between the given dissimilarities δ ij and the derived distances d ij in a lower e-dimensional space. d ij depend on coordinates of the samples we wish to find. Ordinal scaling: Find a configuration of points for which the rank ordering of the interpoint distance is close to the ranking of the values of the given dissimilarities. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

35 Example Multidimensional Scaling from Snow, Kyllonen, Marshalek, 1984 adpated by Gray, Thompson, Nat. Rev. Neuroscience 2004 The correlation of the specific tasks with g-factor of intelligence, strongly in the centre, waekly at the periphery. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

36 Example 2 Multidimensional Scaling J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

37 Example 2 Continued Multidimensional Scaling from statpics fi/2010_07_01_archive.html J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

38 Summary Multidimensional Scaling 1 Feature selection and extraction can be used to reduce the data dimensionality J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

39 Multidimensional Scaling Summary 1 Feature selection and extraction can be used to reduce the data dimensionality 2 Feature selection selects a subset of features. Embedded or wrapper methods are recommended for improved performance. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

40 Summary Multidimensional Scaling 1 Feature selection and extraction can be used to reduce the data dimensionality 2 Feature selection selects a subset of features. Embedded or wrapper methods are recommended for improved performance. 3 Implement the feature selection within the CV-loop (or nested CV loops) J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

41 Summary Multidimensional Scaling 1 Feature selection and extraction can be used to reduce the data dimensionality 2 Feature selection selects a subset of features. Embedded or wrapper methods are recommended for improved performance. 3 Implement the feature selection within the CV-loop (or nested CV loops) 4 Linear feature extraction may be useful. PCA can be used to gain insights of the data. J. Tohka & J. Niemi (TUT-SGN) SGN (4 cr) Chapter 10 February 18, / 38

Feature Selection. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Feature Selection. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani Feature Selection CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Dimensionality reduction Feature selection vs. feature extraction Filter univariate

More information

SGN (4 cr) Chapter 11

SGN (4 cr) Chapter 11 SGN-41006 (4 cr) Chapter 11 Clustering Jussi Tohka & Jari Niemi Department of Signal Processing Tampere University of Technology February 25, 2014 J. Tohka & J. Niemi (TUT-SGN) SGN-41006 (4 cr) Chapter

More information

Feature selection. Term 2011/2012 LSI - FIB. Javier Béjar cbea (LSI - FIB) Feature selection Term 2011/ / 22

Feature selection. Term 2011/2012 LSI - FIB. Javier Béjar cbea (LSI - FIB) Feature selection Term 2011/ / 22 Feature selection Javier Béjar cbea LSI - FIB Term 2011/2012 Javier Béjar cbea (LSI - FIB) Feature selection Term 2011/2012 1 / 22 Outline 1 Dimensionality reduction 2 Projections 3 Attribute selection

More information

Cluster Analysis. Mu-Chun Su. Department of Computer Science and Information Engineering National Central University 2003/3/11 1

Cluster Analysis. Mu-Chun Su. Department of Computer Science and Information Engineering National Central University 2003/3/11 1 Cluster Analysis Mu-Chun Su Department of Computer Science and Information Engineering National Central University 2003/3/11 1 Introduction Cluster analysis is the formal study of algorithms and methods

More information

Dimensionality Reduction, including by Feature Selection.

Dimensionality Reduction, including by Feature Selection. Dimensionality Reduction, including by Feature Selection www.cs.wisc.edu/~dpage/cs760 Goals for the lecture you should understand the following concepts filtering-based feature selection information gain

More information

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Classification Vladimir Curic Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Outline An overview on classification Basics of classification How to choose appropriate

More information

MUSI-6201 Computational Music Analysis

MUSI-6201 Computational Music Analysis MUSI-6201 Computational Music Analysis Part 4.3: Feature Post-Processing alexander lerch November 4, 2015 instantaneous features overview text book Chapter 3: Instantaneous Features (pp. 63 69) sources:

More information

Dimension Reduction CS534

Dimension Reduction CS534 Dimension Reduction CS534 Why dimension reduction? High dimensionality large number of features E.g., documents represented by thousands of words, millions of bigrams Images represented by thousands of

More information

3 Feature Selection & Feature Extraction

3 Feature Selection & Feature Extraction 3 Feature Selection & Feature Extraction Overview: 3.1 Introduction 3.2 Feature Extraction 3.3 Feature Selection 3.3.1 Max-Dependency, Max-Relevance, Min-Redundancy 3.3.2 Relevance Filter 3.3.3 Redundancy

More information

Feature Selection Using Modified-MCA Based Scoring Metric for Classification

Feature Selection Using Modified-MCA Based Scoring Metric for Classification 2011 International Conference on Information Communication and Management IPCSIT vol.16 (2011) (2011) IACSIT Press, Singapore Feature Selection Using Modified-MCA Based Scoring Metric for Classification

More information

Unsupervised Learning

Unsupervised Learning Networks for Pattern Recognition, 2014 Networks for Single Linkage K-Means Soft DBSCAN PCA Networks for Kohonen Maps Linear Vector Quantization Networks for Problems/Approaches in Machine Learning Supervised

More information

Clustering and Visualisation of Data

Clustering and Visualisation of Data Clustering and Visualisation of Data Hiroshi Shimodaira January-March 28 Cluster analysis aims to partition a data set into meaningful or useful groups, based on distances between data points. In some

More information

Statistical Pattern Recognition

Statistical Pattern Recognition Statistical Pattern Recognition Features and Feature Selection Hamid R. Rabiee Jafar Muhammadi Spring 2012 http://ce.sharif.edu/courses/90-91/2/ce725-1/ Agenda Features and Patterns The Curse of Size and

More information

Week 7 Picturing Network. Vahe and Bethany

Week 7 Picturing Network. Vahe and Bethany Week 7 Picturing Network Vahe and Bethany Freeman (2005) - Graphic Techniques for Exploring Social Network Data The two main goals of analyzing social network data are identification of cohesive groups

More information

Instance-based Learning

Instance-based Learning Instance-based Learning Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University February 19 th, 2007 2005-2007 Carlos Guestrin 1 Why not just use Linear Regression? 2005-2007 Carlos Guestrin

More information

Dimension reduction : PCA and Clustering

Dimension reduction : PCA and Clustering Dimension reduction : PCA and Clustering By Hanne Jarmer Slides by Christopher Workman Center for Biological Sequence Analysis DTU The DNA Array Analysis Pipeline Array design Probe design Question Experimental

More information

Linear Methods for Regression and Shrinkage Methods

Linear Methods for Regression and Shrinkage Methods Linear Methods for Regression and Shrinkage Methods Reference: The Elements of Statistical Learning, by T. Hastie, R. Tibshirani, J. Friedman, Springer 1 Linear Regression Models Least Squares Input vectors

More information

Features: representation, normalization, selection. Chapter e-9

Features: representation, normalization, selection. Chapter e-9 Features: representation, normalization, selection Chapter e-9 1 Features Distinguish between instances (e.g. an image that you need to classify), and the features you create for an instance. Features

More information

Multiresponse Sparse Regression with Application to Multidimensional Scaling

Multiresponse Sparse Regression with Application to Multidimensional Scaling Multiresponse Sparse Regression with Application to Multidimensional Scaling Timo Similä and Jarkko Tikka Helsinki University of Technology, Laboratory of Computer and Information Science P.O. Box 54,

More information

Unsupervised Learning

Unsupervised Learning Unsupervised Learning Learning without Class Labels (or correct outputs) Density Estimation Learn P(X) given training data for X Clustering Partition data into clusters Dimensionality Reduction Discover

More information

Preface to the Second Edition. Preface to the First Edition. 1 Introduction 1

Preface to the Second Edition. Preface to the First Edition. 1 Introduction 1 Preface to the Second Edition Preface to the First Edition vii xi 1 Introduction 1 2 Overview of Supervised Learning 9 2.1 Introduction... 9 2.2 Variable Types and Terminology... 9 2.3 Two Simple Approaches

More information

Linear and Non-linear Dimentionality Reduction Applied to Gene Expression Data of Cancer Tissue Samples

Linear and Non-linear Dimentionality Reduction Applied to Gene Expression Data of Cancer Tissue Samples Linear and Non-linear Dimentionality Reduction Applied to Gene Expression Data of Cancer Tissue Samples Franck Olivier Ndjakou Njeunje Applied Mathematics, Statistics, and Scientific Computation University

More information

Basics of Multivariate Modelling and Data Analysis

Basics of Multivariate Modelling and Data Analysis Basics of Multivariate Modelling and Data Analysis Kurt-Erik Häggblom 9. Linear regression with latent variables 9.1 Principal component regression (PCR) 9.2 Partial least-squares regression (PLS) [ mostly

More information

Image Processing. Image Features

Image Processing. Image Features Image Processing Image Features Preliminaries 2 What are Image Features? Anything. What they are used for? Some statements about image fragments (patches) recognition Search for similar patches matching

More information

AN IMPROVED HYBRIDIZED K- MEANS CLUSTERING ALGORITHM (IHKMCA) FOR HIGHDIMENSIONAL DATASET & IT S PERFORMANCE ANALYSIS

AN IMPROVED HYBRIDIZED K- MEANS CLUSTERING ALGORITHM (IHKMCA) FOR HIGHDIMENSIONAL DATASET & IT S PERFORMANCE ANALYSIS AN IMPROVED HYBRIDIZED K- MEANS CLUSTERING ALGORITHM (IHKMCA) FOR HIGHDIMENSIONAL DATASET & IT S PERFORMANCE ANALYSIS H.S Behera Department of Computer Science and Engineering, Veer Surendra Sai University

More information

Introductory Concepts for Voxel-Based Statistical Analysis

Introductory Concepts for Voxel-Based Statistical Analysis Introductory Concepts for Voxel-Based Statistical Analysis John Kornak University of California, San Francisco Department of Radiology and Biomedical Imaging Department of Epidemiology and Biostatistics

More information

Artificial Neural Networks (Feedforward Nets)

Artificial Neural Networks (Feedforward Nets) Artificial Neural Networks (Feedforward Nets) y w 03-1 w 13 y 1 w 23 y 2 w 01 w 21 w 22 w 02-1 w 11 w 12-1 x 1 x 2 6.034 - Spring 1 Single Perceptron Unit y w 0 w 1 w n w 2 w 3 x 0 =1 x 1 x 2 x 3... x

More information

Scaling Techniques in Political Science

Scaling Techniques in Political Science Scaling Techniques in Political Science Eric Guntermann March 14th, 2014 Eric Guntermann Scaling Techniques in Political Science March 14th, 2014 1 / 19 What you need R RStudio R code file Datasets You

More information

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality

More information

Predict Outcomes and Reveal Relationships in Categorical Data

Predict Outcomes and Reveal Relationships in Categorical Data PASW Categories 18 Specifications Predict Outcomes and Reveal Relationships in Categorical Data Unleash the full potential of your data through predictive analysis, statistical learning, perceptual mapping,

More information

CSE 6242 A / CS 4803 DVA. Feb 12, Dimension Reduction. Guest Lecturer: Jaegul Choo

CSE 6242 A / CS 4803 DVA. Feb 12, Dimension Reduction. Guest Lecturer: Jaegul Choo CSE 6242 A / CS 4803 DVA Feb 12, 2013 Dimension Reduction Guest Lecturer: Jaegul Choo CSE 6242 A / CS 4803 DVA Feb 12, 2013 Dimension Reduction Guest Lecturer: Jaegul Choo Data is Too Big To Do Something..

More information

Information Driven Healthcare:

Information Driven Healthcare: Information Driven Healthcare: Machine Learning course Lecture: Feature selection I --- Concepts Centre for Doctoral Training in Healthcare Innovation Dr. Athanasios Tsanas ( Thanasis ), Wellcome Trust

More information

Chapter 12 Feature Selection

Chapter 12 Feature Selection Chapter 12 Feature Selection Xiaogang Su Department of Statistics University of Central Florida - 1 - Outline Why Feature Selection? Categorization of Feature Selection Methods Filter Methods Wrapper Methods

More information

COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS

COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS Toomas Kirt Supervisor: Leo Võhandu Tallinn Technical University Toomas.Kirt@mail.ee Abstract: Key words: For the visualisation

More information

Data Preprocessing. Javier Béjar. URL - Spring 2018 CS - MAI 1/78 BY: $\

Data Preprocessing. Javier Béjar. URL - Spring 2018 CS - MAI 1/78 BY: $\ Data Preprocessing Javier Béjar BY: $\ URL - Spring 2018 C CS - MAI 1/78 Introduction Data representation Unstructured datasets: Examples described by a flat set of attributes: attribute-value matrix Structured

More information

Workload Characterization Techniques

Workload Characterization Techniques Workload Characterization Techniques Raj Jain Washington University in Saint Louis Saint Louis, MO 63130 Jain@cse.wustl.edu These slides are available on-line at: http://www.cse.wustl.edu/~jain/cse567-08/

More information

Information theory methods for feature selection

Information theory methods for feature selection Information theory methods for feature selection Zuzana Reitermanová Department of Computer Science Faculty of Mathematics and Physics Charles University in Prague, Czech Republic Diplomový a doktorandský

More information

Statistical Pattern Recognition

Statistical Pattern Recognition Statistical Pattern Recognition Features and Feature Selection Hamid R. Rabiee Jafar Muhammadi Spring 2014 http://ce.sharif.edu/courses/92-93/2/ce725-2/ Agenda Features and Patterns The Curse of Size and

More information

CS 229 Midterm Review

CS 229 Midterm Review CS 229 Midterm Review Course Staff Fall 2018 11/2/2018 Outline Today: SVMs Kernels Tree Ensembles EM Algorithm / Mixture Models [ Focus on building intuition, less so on solving specific problems. Ask

More information

Big Data Methods. Chapter 5: Machine learning. Big Data Methods, Chapter 5, Slide 1

Big Data Methods. Chapter 5: Machine learning. Big Data Methods, Chapter 5, Slide 1 Big Data Methods Chapter 5: Machine learning Big Data Methods, Chapter 5, Slide 1 5.1 Introduction to machine learning What is machine learning? Concerned with the study and development of algorithms that

More information

Last time... Coryn Bailer-Jones. check and if appropriate remove outliers, errors etc. linear regression

Last time... Coryn Bailer-Jones. check and if appropriate remove outliers, errors etc. linear regression Machine learning, pattern recognition and statistical data modelling Lecture 3. Linear Methods (part 1) Coryn Bailer-Jones Last time... curse of dimensionality local methods quickly become nonlocal as

More information

Statistical Analysis of Metabolomics Data. Xiuxia Du Department of Bioinformatics & Genomics University of North Carolina at Charlotte

Statistical Analysis of Metabolomics Data. Xiuxia Du Department of Bioinformatics & Genomics University of North Carolina at Charlotte Statistical Analysis of Metabolomics Data Xiuxia Du Department of Bioinformatics & Genomics University of North Carolina at Charlotte Outline Introduction Data pre-treatment 1. Normalization 2. Centering,

More information

Applying Supervised Learning

Applying Supervised Learning Applying Supervised Learning When to Consider Supervised Learning A supervised learning algorithm takes a known set of input data (the training set) and known responses to the data (output), and trains

More information

Data Mining - Data. Dr. Jean-Michel RICHER Dr. Jean-Michel RICHER Data Mining - Data 1 / 47

Data Mining - Data. Dr. Jean-Michel RICHER Dr. Jean-Michel RICHER Data Mining - Data 1 / 47 Data Mining - Data Dr. Jean-Michel RICHER 2018 jean-michel.richer@univ-angers.fr Dr. Jean-Michel RICHER Data Mining - Data 1 / 47 Outline 1. Introduction 2. Data preprocessing 3. CPA with R 4. Exercise

More information

A Survey on Pre-processing and Post-processing Techniques in Data Mining

A Survey on Pre-processing and Post-processing Techniques in Data Mining , pp. 99-128 http://dx.doi.org/10.14257/ijdta.2014.7.4.09 A Survey on Pre-processing and Post-processing Techniques in Data Mining Divya Tomar and Sonali Agarwal Indian Institute of Information Technology,

More information

Feature Selection in Knowledge Discovery

Feature Selection in Knowledge Discovery Feature Selection in Knowledge Discovery Susana Vieira Technical University of Lisbon, Instituto Superior Técnico Department of Mechanical Engineering, Center of Intelligent Systems, IDMEC-LAETA Av. Rovisco

More information

Flexible-Hybrid Sequential Floating Search in Statistical Feature Selection

Flexible-Hybrid Sequential Floating Search in Statistical Feature Selection Flexible-Hybrid Sequential Floating Search in Statistical Feature Selection Petr Somol 1,2, Jana Novovičová 1,2, and Pavel Pudil 2,1 1 Dept. of Pattern Recognition, Institute of Information Theory and

More information

Statistical Pattern Recognition

Statistical Pattern Recognition Statistical Pattern Recognition Features and Feature Selection Hamid R. Rabiee Jafar Muhammadi Spring 2013 http://ce.sharif.edu/courses/91-92/2/ce725-1/ Agenda Features and Patterns The Curse of Size and

More information

The Anatomical Equivalence Class Formulation and its Application to Shape-based Computational Neuroanatomy

The Anatomical Equivalence Class Formulation and its Application to Shape-based Computational Neuroanatomy The Anatomical Equivalence Class Formulation and its Application to Shape-based Computational Neuroanatomy Sokratis K. Makrogiannis, PhD From post-doctoral research at SBIA lab, Department of Radiology,

More information

Variable Selection 6.783, Biomedical Decision Support

Variable Selection 6.783, Biomedical Decision Support 6.783, Biomedical Decision Support (lrosasco@mit.edu) Department of Brain and Cognitive Science- MIT November 2, 2009 About this class Why selecting variables Approaches to variable selection Sparsity-based

More information

Principal Component Image Interpretation A Logical and Statistical Approach

Principal Component Image Interpretation A Logical and Statistical Approach Principal Component Image Interpretation A Logical and Statistical Approach Md Shahid Latif M.Tech Student, Department of Remote Sensing, Birla Institute of Technology, Mesra Ranchi, Jharkhand-835215 Abstract

More information

Regularization and model selection

Regularization and model selection CS229 Lecture notes Andrew Ng Part VI Regularization and model selection Suppose we are trying select among several different models for a learning problem. For instance, we might be using a polynomial

More information

Multidimensional scaling Based in part on slides from textbook, slides of Susan Holmes. October 10, Statistics 202: Data Mining

Multidimensional scaling Based in part on slides from textbook, slides of Susan Holmes. October 10, Statistics 202: Data Mining Multidimensional scaling Based in part on slides from textbook, slides of Susan Holmes October 10, 2012 1 / 1 Multidimensional scaling A visual tool Recall the PCA scores were X V = U where X = HX S 1/2

More information

CBioVikings. Richard Röttger. Copenhagen February 2 nd, Clustering of Biomedical Data

CBioVikings. Richard Röttger. Copenhagen February 2 nd, Clustering of Biomedical Data CBioVikings Copenhagen February 2 nd, Richard Röttger 1 Who is talking? 2 Resources Go to http://imada.sdu.dk/~roettger/teaching/cbiovikings.php You will find The dataset These slides An overview paper

More information

10-701/15-781, Fall 2006, Final

10-701/15-781, Fall 2006, Final -7/-78, Fall 6, Final Dec, :pm-8:pm There are 9 questions in this exam ( pages including this cover sheet). If you need more room to work out your answer to a question, use the back of the page and clearly

More information

IMAGE ANALYSIS, CLASSIFICATION, and CHANGE DETECTION in REMOTE SENSING

IMAGE ANALYSIS, CLASSIFICATION, and CHANGE DETECTION in REMOTE SENSING SECOND EDITION IMAGE ANALYSIS, CLASSIFICATION, and CHANGE DETECTION in REMOTE SENSING ith Algorithms for ENVI/IDL Morton J. Canty с*' Q\ CRC Press Taylor &. Francis Group Boca Raton London New York CRC

More information

Lecture on Modeling Tools for Clustering & Regression

Lecture on Modeling Tools for Clustering & Regression Lecture on Modeling Tools for Clustering & Regression CS 590.21 Analysis and Modeling of Brain Networks Department of Computer Science University of Crete Data Clustering Overview Organizing data into

More information

Face Recognition using Eigenfaces SMAI Course Project

Face Recognition using Eigenfaces SMAI Course Project Face Recognition using Eigenfaces SMAI Course Project Satarupa Guha IIIT Hyderabad 201307566 satarupa.guha@research.iiit.ac.in Ayushi Dalmia IIIT Hyderabad 201307565 ayushi.dalmia@research.iiit.ac.in Abstract

More information

Nonlinear projections. Motivation. High-dimensional. data are. Perceptron) ) or RBFN. Multi-Layer. Example: : MLP (Multi(

Nonlinear projections. Motivation. High-dimensional. data are. Perceptron) ) or RBFN. Multi-Layer. Example: : MLP (Multi( Nonlinear projections Université catholique de Louvain (Belgium) Machine Learning Group http://www.dice.ucl ucl.ac.be/.ac.be/mlg/ 1 Motivation High-dimensional data are difficult to represent difficult

More information

Recognizing Handwritten Digits Using the LLE Algorithm with Back Propagation

Recognizing Handwritten Digits Using the LLE Algorithm with Back Propagation Recognizing Handwritten Digits Using the LLE Algorithm with Back Propagation Lori Cillo, Attebury Honors Program Dr. Rajan Alex, Mentor West Texas A&M University Canyon, Texas 1 ABSTRACT. This work is

More information

Clustering. CS294 Practical Machine Learning Junming Yin 10/09/06

Clustering. CS294 Practical Machine Learning Junming Yin 10/09/06 Clustering CS294 Practical Machine Learning Junming Yin 10/09/06 Outline Introduction Unsupervised learning What is clustering? Application Dissimilarity (similarity) of objects Clustering algorithm K-means,

More information

A Distance-Based Classifier Using Dissimilarity Based on Class Conditional Probability and Within-Class Variation. Kwanyong Lee 1 and Hyeyoung Park 2

A Distance-Based Classifier Using Dissimilarity Based on Class Conditional Probability and Within-Class Variation. Kwanyong Lee 1 and Hyeyoung Park 2 A Distance-Based Classifier Using Dissimilarity Based on Class Conditional Probability and Within-Class Variation Kwanyong Lee 1 and Hyeyoung Park 2 1. Department of Computer Science, Korea National Open

More information

INF 4300 Classification III Anne Solberg The agenda today:

INF 4300 Classification III Anne Solberg The agenda today: INF 4300 Classification III Anne Solberg 28.10.15 The agenda today: More on estimating classifier accuracy Curse of dimensionality and simple feature selection knn-classification K-means clustering 28.10.15

More information

General Instructions. Questions

General Instructions. Questions CS246: Mining Massive Data Sets Winter 2018 Problem Set 2 Due 11:59pm February 8, 2018 Only one late period is allowed for this homework (11:59pm 2/13). General Instructions Submission instructions: These

More information

Feature Selection Using Principal Feature Analysis

Feature Selection Using Principal Feature Analysis Feature Selection Using Principal Feature Analysis Ira Cohen Qi Tian Xiang Sean Zhou Thomas S. Huang Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign Urbana,

More information

I How does the formulation (5) serve the purpose of the composite parameterization

I How does the formulation (5) serve the purpose of the composite parameterization Supplemental Material to Identifying Alzheimer s Disease-Related Brain Regions from Multi-Modality Neuroimaging Data using Sparse Composite Linear Discrimination Analysis I How does the formulation (5)

More information

CIE L*a*b* color model

CIE L*a*b* color model CIE L*a*b* color model To further strengthen the correlation between the color model and human perception, we apply the following non-linear transformation: with where (X n,y n,z n ) are the tristimulus

More information

Classification. Slide sources:

Classification. Slide sources: Classification Slide sources: Gideon Dror, Academic College of TA Yaffo Nathan Ifill, Leicester MA4102 Data Mining and Neural Networks Andrew Moore, CMU : http://www.cs.cmu.edu/~awm/tutorials 1 Outline

More information

Discriminate Analysis

Discriminate Analysis Discriminate Analysis Outline Introduction Linear Discriminant Analysis Examples 1 Introduction What is Discriminant Analysis? Statistical technique to classify objects into mutually exclusive and exhaustive

More information

Chemometrics. Description of Pirouette Algorithms. Technical Note. Abstract

Chemometrics. Description of Pirouette Algorithms. Technical Note. Abstract 19-1214 Chemometrics Technical Note Description of Pirouette Algorithms Abstract This discussion introduces the three analysis realms available in Pirouette and briefly describes each of the algorithms

More information

Principal Component Analysis (PCA) is a most practicable. statistical technique. Its application plays a major role in many

Principal Component Analysis (PCA) is a most practicable. statistical technique. Its application plays a major role in many CHAPTER 3 PRINCIPAL COMPONENT ANALYSIS ON EIGENFACES 2D AND 3D MODEL 3.1 INTRODUCTION Principal Component Analysis (PCA) is a most practicable statistical technique. Its application plays a major role

More information

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Classification Vladimir Curic Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Outline An overview on classification Basics of classification How to choose appropriate

More information

CHAPTER 4: CLUSTER ANALYSIS

CHAPTER 4: CLUSTER ANALYSIS CHAPTER 4: CLUSTER ANALYSIS WHAT IS CLUSTER ANALYSIS? A cluster is a collection of data-objects similar to one another within the same group & dissimilar to the objects in other groups. Cluster analysis

More information

Sparse and large-scale learning with heterogeneous data

Sparse and large-scale learning with heterogeneous data Sparse and large-scale learning with heterogeneous data February 15, 2007 Gert Lanckriet (gert@ece.ucsd.edu) IEEE-SDCIS In this talk Statistical machine learning Techniques: roots in classical statistics

More information

The exam is closed book, closed notes except your one-page cheat sheet.

The exam is closed book, closed notes except your one-page cheat sheet. CS 189 Fall 2015 Introduction to Machine Learning Final Please do not turn over the page before you are instructed to do so. You have 2 hours and 50 minutes. Please write your initials on the top-right

More information

6. Dicretization methods 6.1 The purpose of discretization

6. Dicretization methods 6.1 The purpose of discretization 6. Dicretization methods 6.1 The purpose of discretization Often data are given in the form of continuous values. If their number is huge, model building for such data can be difficult. Moreover, many

More information

5 Learning hypothesis classes (16 points)

5 Learning hypothesis classes (16 points) 5 Learning hypothesis classes (16 points) Consider a classification problem with two real valued inputs. For each of the following algorithms, specify all of the separators below that it could have generated

More information

2. Data Preprocessing

2. Data Preprocessing 2. Data Preprocessing Contents of this Chapter 2.1 Introduction 2.2 Data cleaning 2.3 Data integration 2.4 Data transformation 2.5 Data reduction Reference: [Han and Kamber 2006, Chapter 2] SFU, CMPT 459

More information

Stats fest Multivariate analysis. Multivariate analyses. Aims. Multivariate analyses. Objects. Variables

Stats fest Multivariate analysis. Multivariate analyses. Aims. Multivariate analyses. Objects. Variables Stats fest 7 Multivariate analysis murray.logan@sci.monash.edu.au Multivariate analyses ims Data reduction Reduce large numbers of variables into a smaller number that adequately summarize the patterns

More information

FEATURE SELECTION TECHNIQUES

FEATURE SELECTION TECHNIQUES CHAPTER-2 FEATURE SELECTION TECHNIQUES 2.1. INTRODUCTION Dimensionality reduction through the choice of an appropriate feature subset selection, results in multiple uses including performance upgrading,

More information

Clustering. Informal goal. General types of clustering. Applications: Clustering in information search and analysis. Example applications in search

Clustering. Informal goal. General types of clustering. Applications: Clustering in information search and analysis. Example applications in search Informal goal Clustering Given set of objects and measure of similarity between them, group similar objects together What mean by similar? What is good grouping? Computation time / quality tradeoff 1 2

More information

Detecting Hippocampal Shape Changes in Alzheimer s Disease using Statistical Shape Models

Detecting Hippocampal Shape Changes in Alzheimer s Disease using Statistical Shape Models Detecting Hippocampal Shape Changes in Alzheimer s Disease using Statistical Shape Models Kaikai Shen a,b, Pierrick Bourgeat a, Jurgen Fripp a, Fabrice Meriaudeau b, Olivier Salvado a and the Alzheimer

More information

The Curse of Dimensionality

The Curse of Dimensionality The Curse of Dimensionality ACAS 2002 p1/66 Curse of Dimensionality The basic idea of the curse of dimensionality is that high dimensional data is difficult to work with for several reasons: Adding more

More information

Collaborative filtering based on a random walk model on a graph

Collaborative filtering based on a random walk model on a graph Collaborative filtering based on a random walk model on a graph Marco Saerens, Francois Fouss, Alain Pirotte, Luh Yen, Pierre Dupont (UCL) Jean-Michel Renders (Xerox Research Europe) Some recent methods:

More information

What is machine learning?

What is machine learning? Machine learning, pattern recognition and statistical data modelling Lecture 12. The last lecture Coryn Bailer-Jones 1 What is machine learning? Data description and interpretation finding simpler relationship

More information

Data preprocessing Functional Programming and Intelligent Algorithms

Data preprocessing Functional Programming and Intelligent Algorithms Data preprocessing Functional Programming and Intelligent Algorithms Que Tran Høgskolen i Ålesund 20th March 2017 1 Why data preprocessing? Real-world data tend to be dirty incomplete: lacking attribute

More information

Probabilistic Approaches

Probabilistic Approaches Probabilistic Approaches Chirayu Wongchokprasitti, PhD University of Pittsburgh Center for Causal Discovery Department of Biomedical Informatics chw20@pitt.edu http://www.pitt.edu/~chw20 Overview Independence

More information

A Course in Machine Learning

A Course in Machine Learning A Course in Machine Learning Hal Daumé III 13 UNSUPERVISED LEARNING If you have access to labeled training data, you know what to do. This is the supervised setting, in which you have a teacher telling

More information

Mapping of Hierarchical Activation in the Visual Cortex Suman Chakravartula, Denise Jones, Guillaume Leseur CS229 Final Project Report. Autumn 2008.

Mapping of Hierarchical Activation in the Visual Cortex Suman Chakravartula, Denise Jones, Guillaume Leseur CS229 Final Project Report. Autumn 2008. Mapping of Hierarchical Activation in the Visual Cortex Suman Chakravartula, Denise Jones, Guillaume Leseur CS229 Final Project Report. Autumn 2008. Introduction There is much that is unknown regarding

More information

Operators-Based on Second Derivative double derivative Laplacian operator Laplacian Operator Laplacian Of Gaussian (LOG) Operator LOG

Operators-Based on Second Derivative double derivative Laplacian operator Laplacian Operator Laplacian Of Gaussian (LOG) Operator LOG Operators-Based on Second Derivative The principle of edge detection based on double derivative is to detect only those points as edge points which possess local maxima in the gradient values. Laplacian

More information

Interpolation is a basic tool used extensively in tasks such as zooming, shrinking, rotating, and geometric corrections.

Interpolation is a basic tool used extensively in tasks such as zooming, shrinking, rotating, and geometric corrections. Image Interpolation 48 Interpolation is a basic tool used extensively in tasks such as zooming, shrinking, rotating, and geometric corrections. Fundamentally, interpolation is the process of using known

More information

MTTS1 Dimensionality Reduction and Visualization Spring 2014 Jaakko Peltonen

MTTS1 Dimensionality Reduction and Visualization Spring 2014 Jaakko Peltonen MTTS1 Dimensionality Reduction and Visualization Spring 2014 Jaakko Peltonen Lecture 2: Feature selection Feature Selection feature selection (also called variable selection): choosing k < d important

More information

Network Traffic Measurements and Analysis

Network Traffic Measurements and Analysis DEIB - Politecnico di Milano Fall, 2017 Introduction Often, we have only a set of features x = x 1, x 2,, x n, but no associated response y. Therefore we are not interested in prediction nor classification,

More information

Function approximation using RBF network. 10 basis functions and 25 data points.

Function approximation using RBF network. 10 basis functions and 25 data points. 1 Function approximation using RBF network F (x j ) = m 1 w i ϕ( x j t i ) i=1 j = 1... N, m 1 = 10, N = 25 10 basis functions and 25 data points. Basis function centers are plotted with circles and data

More information

Feature Subset Selection on Multivariate Time Series with Extremely Large Spatial Features

Feature Subset Selection on Multivariate Time Series with Extremely Large Spatial Features Feature Subset Selection on Multivariate Time Series with Extremely Large Spatial Features Hyunjin Yoon and Cyrus Shahabi Department of Computer Science University of Southern California Los Angeles, CA

More information

Data Mining Practical Machine Learning Tools and Techniques. Slides for Chapter 6 of Data Mining by I. H. Witten and E. Frank

Data Mining Practical Machine Learning Tools and Techniques. Slides for Chapter 6 of Data Mining by I. H. Witten and E. Frank Data Mining Practical Machine Learning Tools and Techniques Slides for Chapter 6 of Data Mining by I. H. Witten and E. Frank Implementation: Real machine learning schemes Decision trees Classification

More information

Face detection and recognition. Detection Recognition Sally

Face detection and recognition. Detection Recognition Sally Face detection and recognition Detection Recognition Sally Face detection & recognition Viola & Jones detector Available in open CV Face recognition Eigenfaces for face recognition Metric learning identification

More information

MSA220 - Statistical Learning for Big Data

MSA220 - Statistical Learning for Big Data MSA220 - Statistical Learning for Big Data Lecture 13 Rebecka Jörnsten Mathematical Sciences University of Gothenburg and Chalmers University of Technology Clustering Explorative analysis - finding groups

More information

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging

Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging 1 CS 9 Final Project Classification of Subject Motion for Improved Reconstruction of Dynamic Magnetic Resonance Imaging Feiyu Chen Department of Electrical Engineering ABSTRACT Subject motion is a significant

More information

Learning from High Dimensional fmri Data using Random Projections

Learning from High Dimensional fmri Data using Random Projections Learning from High Dimensional fmri Data using Random Projections Author: Madhu Advani December 16, 011 Introduction The term the Curse of Dimensionality refers to the difficulty of organizing and applying

More information