Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
|
|
- Lucy Welch
- 5 years ago
- Views:
Transcription
1 Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering May
2 2 Content 1. Introduction 2. Proposed Technique 2.1 Learning Fast Localized Spectral Filters 2.2 Graph Coarsening 2.3 Fast Pooling of Graph Signals 3. Numerical Experiments
3 3 GCNN
4 4 Abstract In this work, we generalize CNN from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words embedding, represented by graphs. We present a formulation of CNNs in the context of spectral graph theory. Importantly, the proposed technique offers the same linear computational complexity and constant learning complexity as classical CNNs
5 5 Introduction The major bottleneck of generalizing CNNs to graphs, and one of the primary goals of this work, is the definition of localized graph filters which are efficient to evaluate and learn. CNNs extract the local stationarity property of the input data or signals by revealing local features that are shared across the data domain. These similar features are identified with localized convolutional filters or kernels. Localized kernels or compactly supported filters refer to filters that extract local features independently of the input data size, with a support size that can be much smaller than the input size.
6 6 Contributions Spectral formulation: GCNN built on established tools in graph signal processing (GSP). Strictly localized filters: Enhancing [4], the proposed spectral filters are provable to be strictly localized in a ball of radius K. Low computational complexity: The evaluation complexity of our filters is linear.this method avoids the Fourier basis altogether, thus the expensive EVD necessary to compute it as well as the need to store the basis, a matrix of size n**2. Besides the data, our method only requires to store the Laplacian, a sparse matrix. Efficient pooling: We propose an efficient pooling strategy on graphs which, after a rearrangement of the vertices as a binary tree structure, is analog to pooling of 1D signals. Experimental results: superior both in accuracy and complexity to the pioneer spectral graph CNN[4]. And it performs similarly to a classical CNNs on MNIST.
7 7 Proposed Technique Design of localized convolutional filters on graphs; Graph coarsening procedure that groups together similar vertices; Graph pooling operation that trades spatial resolution for higher filter resolution.
8 8 Learning Fast Localized Spectral Filters There are two strategies to define convolutional filters: 1. Spatial approach: challenge of matching local neighborhoods 2. Spectral approach: via convolutions with a Kronecker delta implemented in the spectral domain. The convolution theorem defines convolutions as linear operators that diagonalize in the Fourier basis. - However, a filter defined in the spectral domain is not naturally localized and translations are costly due to the O(n**2) multiplication with the graph Fourier basis. But it can be overcome.
9 9 Learning Fast Localized Spectral Filters 1. Graph Fourier Transform 2. Polynomial parametrization for localized filters 3. Recursive formulation for fast filtering
10 10 Graph Fourier Transform Too many maths symbols, I just conclude its tuition here: 1. Transform the undirected graph into graph Laplacian, which is Degree Matrix - Adjacency Matrix, then normalized it. 2. Find out the Fourier basis U (The Laplacian is indeed diagonalized by the Fourier basis) 3. The convolution operation become an element-wise Hadamard product in the Fourier domain.
11 11 Polynomial parametrization for localized filters 1. Graph Fourier Transform's learning complexity is quite high and are not localized in space. These issue can be overcome with the use of a polynomial filter. 2. Considering a smoothing kernal, such as splines.
12 12 Polynomial parametrization for localized filters 1. Graph Fourier Transform's learning complexity is quite high and are not localized in space. These issue can be overcome with the use of a polynomial filter. 2. Considering a smoothing kernal, such as splines.
13 13 Recursive formulation for fast filtering Using Polynomial parametrization is cool but the cost to filter a signal x is still high.(actually these previous methods were proposed by [4]) So they come up with their methods: a polynomial function that can be computed recursively from L, as L is sparse, so the cost is much lower. Approximation methods: 1. Chebyshev expansion(they use this one in their experiments) 2. Lanczos Algorithm
14 14 Learning the filters Actually is the same as classical CNN, using Back Propagation over a mini-batch of S samples.
15 15 Graph Coarsening After the Convolution operation, we need to think about the pooling operation. So we come across a problem: it requires meaningful neighborhoods on graphs, where similar vertices are clustered together. Doing this for multiple layers is equivalent to a multi-scale clustering of the graph that preserves local geometric structures. While this problem is NP-hard, so they use METIS, a greedy alogrithm to compute successive coarser versions of a given graph.
16 16 Graph Coarsening After the Convolution operation, we need to think about the pooling operation. So we come across a problem: it requires meaningful neighborhoods on graphs, where similar vertices are clustered together. Doing this for multiple layers is equivalent to a multi-scale clustering of the graph that preserves local geometric structures. While this problem is NP-hard, so they use METIS, a greedy alogrithm to compute successive coarser versions of a given graph.
17 17 Fast Pooling
18
Lecture 10 CNNs on Graphs
Lecture 10 CNNs on Graphs CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago April 26, 2017 Two Scenarios For CNNs on graphs, we have two distinct scenarios: Scenario 1: Each
More informationFrom processing to learning on graphs
From processing to learning on graphs Patrick Pérez Maths and Images in Paris IHP, 2 March 2017 Signals on graphs Natural graph: mesh, network, etc., related to a real structure, various signals can live
More informationInception Network Overview. David White CS793
Inception Network Overview David White CS793 So, Leonardo DiCaprio dreams about dreaming... https://m.media-amazon.com/images/m/mv5bmjaxmzy3njcxnf5bml5banbnxkftztcwnti5otm0mw@@._v1_sy1000_cr0,0,675,1 000_AL_.jpg
More informationSpectral Coding of Three-Dimensional Mesh Geometry Information Using Dual Graph
Spectral Coding of Three-Dimensional Mesh Geometry Information Using Dual Graph Sung-Yeol Kim, Seung-Uk Yoon, and Yo-Sung Ho Gwangju Institute of Science and Technology (GIST) 1 Oryong-dong, Buk-gu, Gwangju,
More informationGRAPH LEARNING UNDER SPARSITY PRIORS. Hermina Petric Maretic, Dorina Thanou and Pascal Frossard
GRAPH LEARNING UNDER SPARSITY PRIORS Hermina Petric Maretic, Dorina Thanou and Pascal Frossard Signal Processing Laboratory (LTS4), EPFL, Switzerland ABSTRACT Graph signals offer a very generic and natural
More informationGraph Partitioning for High-Performance Scientific Simulations. Advanced Topics Spring 2008 Prof. Robert van Engelen
Graph Partitioning for High-Performance Scientific Simulations Advanced Topics Spring 2008 Prof. Robert van Engelen Overview Challenges for irregular meshes Modeling mesh-based computations as graphs Static
More informationNeighborhood-Preserving Translations on Graphs
Neighborhood-Preserving Translations on Graphs Nicolas Grelier, Bastien Pasdeloup, Jean-Charles Vialatte and Vincent Gripon Télécom Bretagne, France name.surname@telecom-bretagne.eu arxiv:1606.02479v1
More informationScaled representations
Scaled representations Big bars (resp. spots, hands, etc.) and little bars are both interesting Stripes and hairs, say Inefficient to detect big bars with big filters And there is superfluous detail in
More informationDeep Learning on Graphs
Deep Learning on Graphs with Graph Convolutional Networks Hidden layer Hidden layer Input Output ReLU ReLU, 22 March 2017 joint work with Max Welling (University of Amsterdam) BDL Workshop @ NIPS 2016
More informationScalable Clustering of Signed Networks Using Balance Normalized Cut
Scalable Clustering of Signed Networks Using Balance Normalized Cut Kai-Yang Chiang,, Inderjit S. Dhillon The 21st ACM International Conference on Information and Knowledge Management (CIKM 2012) Oct.
More informationLecture 11: Clustering and the Spectral Partitioning Algorithm A note on randomized algorithm, Unbiased estimates
CSE 51: Design and Analysis of Algorithms I Spring 016 Lecture 11: Clustering and the Spectral Partitioning Algorithm Lecturer: Shayan Oveis Gharan May nd Scribe: Yueqi Sheng Disclaimer: These notes have
More informationDesign of Orthogonal Graph Wavelet Filter Banks
Design of Orthogonal Graph Wavelet Filter Banks Xi ZHANG Department of Communication Engineering and Informatics The University of Electro-Communications Chofu-shi, Tokyo, 182-8585 JAPAN E-mail: zhangxi@uec.ac.jp
More informationSurfaces, meshes, and topology
Surfaces from Point Samples Surfaces, meshes, and topology A surface is a 2-manifold embedded in 3- dimensional Euclidean space Such surfaces are often approximated by triangle meshes 2 1 Triangle mesh
More informationSplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels Matthias Fey, Jan Eric Lenssen, Frank Weichert, Heinrich Mu ller Department of Computer Graphics TU Dortmund University {matthiasfey,janericlenssen}@udoedu
More informationImage Processing. Filtering. Slide 1
Image Processing Filtering Slide 1 Preliminary Image generation Original Noise Image restoration Result Slide 2 Preliminary Classic application: denoising However: Denoising is much more than a simple
More informationMachine Learning : Clustering, Self-Organizing Maps
Machine Learning Clustering, Self-Organizing Maps 12/12/2013 Machine Learning : Clustering, Self-Organizing Maps Clustering The task: partition a set of objects into meaningful subsets (clusters). The
More informationSPECTRAL SPARSIFICATION IN SPECTRAL CLUSTERING
SPECTRAL SPARSIFICATION IN SPECTRAL CLUSTERING Alireza Chakeri, Hamidreza Farhidzadeh, Lawrence O. Hall Department of Computer Science and Engineering College of Engineering University of South Florida
More informationCS 664 Slides #11 Image Segmentation. Prof. Dan Huttenlocher Fall 2003
CS 664 Slides #11 Image Segmentation Prof. Dan Huttenlocher Fall 2003 Image Segmentation Find regions of image that are coherent Dual of edge detection Regions vs. boundaries Related to clustering problems
More informationSpectral Clustering and Community Detection in Labeled Graphs
Spectral Clustering and Community Detection in Labeled Graphs Brandon Fain, Stavros Sintos, Nisarg Raval Machine Learning (CompSci 571D / STA 561D) December 7, 2015 {btfain, nisarg, ssintos} at cs.duke.edu
More informationCS 140: Sparse Matrix-Vector Multiplication and Graph Partitioning
CS 140: Sparse Matrix-Vector Multiplication and Graph Partitioning Parallel sparse matrix-vector product Lay out matrix and vectors by rows y(i) = sum(a(i,j)*x(j)) Only compute terms with A(i,j) 0 P0 P1
More informationGraph Based Convolutional Neural Network
EDWARDS, XIE: GRAPH CONVOLUTIONAL NEURAL NETWORK 1 Graph Based Convolutional Neural Network Michael Edwards Xianghua Xie http://www.csvision.swan.ac.uk Swansea University Swansea, UK Abstract The benefit
More informationCS 534: Computer Vision Texture
CS 534: Computer Vision Texture Ahmed Elgammal Dept of Computer Science CS 534 Texture - 1 Outlines Finding templates by convolution What is Texture Co-occurrence matrices for texture Spatial Filtering
More informationDeep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group
Deep Learning Vladimir Golkov Technical University of Munich Computer Vision Group 1D Input, 1D Output target input 2 2D Input, 1D Output: Data Distribution Complexity Imagine many dimensions (data occupies
More informationOptimization in the Big Data Regime 5: Parallelization? Sham M. Kakade
Optimization in the Big Data Regime 5: Parallelization? Sham M. Kakade Machine Learning for Big Data CSE547/STAT548 University of Washington S. M. Kakade (UW) Optimization for Big data 1 / 21 Announcements...
More informationOPTIMAL DYNAMIC LOAD BALANCE IN DISTRIBUTED SYSTEMS FOR CLIENT SERVER ASSIGNMENT
OPTIMAL DYNAMIC LOAD BALANCE IN DISTRIBUTED SYSTEMS FOR CLIENT SERVER ASSIGNMENT D.SARITHA Department of CS&SE, Andhra University Visakhapatnam, Andhra Pradesh Ch. SATYANANDA REDDY Professor, Department
More informationSpectral Graph Sparsification: overview of theory and practical methods. Yiannis Koutis. University of Puerto Rico - Rio Piedras
Spectral Graph Sparsification: overview of theory and practical methods Yiannis Koutis University of Puerto Rico - Rio Piedras Graph Sparsification or Sketching Compute a smaller graph that preserves some
More informationHierarchical Multi level Approach to graph clustering
Hierarchical Multi level Approach to graph clustering by: Neda Shahidi neda@cs.utexas.edu Cesar mantilla, cesar.mantilla@mail.utexas.edu Advisor: Dr. Inderjit Dhillon Introduction Data sets can be presented
More informationLecture 2 Notes. Outline. Neural Networks. The Big Idea. Architecture. Instructors: Parth Shah, Riju Pahwa
Instructors: Parth Shah, Riju Pahwa Lecture 2 Notes Outline 1. Neural Networks The Big Idea Architecture SGD and Backpropagation 2. Convolutional Neural Networks Intuition Architecture 3. Recurrent Neural
More informationCS 534: Computer Vision Texture
CS 534: Computer Vision Texture Spring 2004 Ahmed Elgammal Dept of Computer Science CS 534 Ahmed Elgammal Texture - 1 Outlines Finding templates by convolution What is Texture Co-occurrence matrecis for
More informationDeep 3D Machine Learning for Reconstruction and Repair of 3D Surfaces
Deep 3D Machine Learning for Reconstruction and Repair of 3D Surfaces TalkID 23152 This session will give the audience a quick overview of recent developments in the field of 3D surface analysis with deep
More informationAarti Singh. Machine Learning / Slides Courtesy: Eric Xing, M. Hein & U.V. Luxburg
Spectral Clustering Aarti Singh Machine Learning 10-701/15-781 Apr 7, 2010 Slides Courtesy: Eric Xing, M. Hein & U.V. Luxburg 1 Data Clustering Graph Clustering Goal: Given data points X1,, Xn and similarities
More informationA New Approach For Regularized Image Interpolation
S. E. El-Khamy 1, M. M. Hadhoud 2, M. I. Dessouky 3, B. M. Salam 3, F. E. Abd El-Samie 4 1 Dept. of Electrical Eng., Faculty of Engineering, Alexandria Univ., Alexandria, Egypt. elkhamy@ieee.org 2 Dept.
More informationOverview. Spectral Processing of Point- Sampled Geometry. Introduction. Introduction. Fourier Transform. Fourier Transform
Overview Spectral Processing of Point- Sampled Geometry Introduction Fourier transform Spectral processing pipeline Spectral filtering Adaptive subsampling Summary Point-Based Computer Graphics Markus
More informationFeature Selection for fmri Classification
Feature Selection for fmri Classification Chuang Wu Program of Computational Biology Carnegie Mellon University Pittsburgh, PA 15213 chuangw@andrew.cmu.edu Abstract The functional Magnetic Resonance Imaging
More informationDeep Learning and Its Applications
Convolutional Neural Network and Its Application in Image Recognition Oct 28, 2016 Outline 1 A Motivating Example 2 The Convolutional Neural Network (CNN) Model 3 Training the CNN Model 4 Issues and Recent
More informationSIFT - scale-invariant feature transform Konrad Schindler
SIFT - scale-invariant feature transform Konrad Schindler Institute of Geodesy and Photogrammetry Invariant interest points Goal match points between images with very different scale, orientation, projective
More informationMachine Learning 13. week
Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of
More informationParallelization in the Big Data Regime 5: Data Parallelization? Sham M. Kakade
Parallelization in the Big Data Regime 5: Data Parallelization? Sham M. Kakade Machine Learning for Big Data CSE547/STAT548 University of Washington S. M. Kakade (UW) Optimization for Big data 1 / 23 Announcements...
More informationCommunity Detection. Community
Community Detection Community In social sciences: Community is formed by individuals such that those within a group interact with each other more frequently than with those outside the group a.k.a. group,
More informationRegularization and Markov Random Fields (MRF) CS 664 Spring 2008
Regularization and Markov Random Fields (MRF) CS 664 Spring 2008 Regularization in Low Level Vision Low level vision problems concerned with estimating some quantity at each pixel Visual motion (u(x,y),v(x,y))
More informationGraph Wavelets and Filter Banks Designs in Graph Spectral Domain
at CMU Graph Wavelets and Filter Banks Designs in Graph Spectral Domain Yuichi Tanaka Tokyo University of Agriculture and Technology PRESTO, Japan Science and Technology Agency ytnk@cc.tuat.ac.jp This
More informationGabor and Wavelet transforms for signals defined on graphs An invitation to signal processing on graphs
Gabor and Wavelet transforms for signals defined on graphs An invitation to signal processing on graphs Benjamin Ricaud Signal Processing Lab 2, EPFL Lausanne, Switzerland SPLab, Brno, 10/2013 B. Ricaud
More informationMar. 20 Math 2335 sec 001 Spring 2014
Mar. 20 Math 2335 sec 001 Spring 2014 Chebyshev Polynomials Definition: For an integer n 0 define the function ( ) T n (x) = cos n cos 1 (x), 1 x 1. It can be shown that T n is a polynomial of degree n.
More informationKernels vs. DNNs for Speech Recognition
Kernels vs. DNNs for Speech Recognition Joint work with: Columbia: Linxi (Jim) Fan, Michael Collins (my advisor) USC: Zhiyun Lu, Kuan Liu, Alireza Bagheri Garakani, Dong Guo, Aurélien Bellet, Fei Sha IBM:
More informationNative mesh ordering with Scotch 4.0
Native mesh ordering with Scotch 4.0 François Pellegrini INRIA Futurs Project ScAlApplix pelegrin@labri.fr Abstract. Sparse matrix reordering is a key issue for the the efficient factorization of sparse
More informationIntroduc1on to Computa1onal Manifolds and Applica1ons
Trimester Program on Computa1onal Manifolds and Applica1ons Introduc1on to Computa1onal Manifolds and Applica1ons Manifold Harmonics Luis Gustavo Nonato Depto Matemá3ca Aplicada e Esta9s3ca ICMC- USP-
More informationBlind Identification of Graph Filters with Multiple Sparse Inputs
Blind Identification of Graph Filters with Multiple Sparse Inputs Santiago Segarra, Antonio G. Marques, Gonzalo Mateos & Alejandro Ribeiro Dept. of Electrical and Systems Engineering University of Pennsylvania
More informationLatent Space Model for Road Networks to Predict Time-Varying Traffic. Presented by: Rob Fitzgerald Spring 2017
Latent Space Model for Road Networks to Predict Time-Varying Traffic Presented by: Rob Fitzgerald Spring 2017 Definition of Latent https://en.oxforddictionaries.com/definition/latent Latent Space Model?
More informationDigital Image Processing. Prof. P. K. Biswas. Department of Electronic & Electrical Communication Engineering
Digital Image Processing Prof. P. K. Biswas Department of Electronic & Electrical Communication Engineering Indian Institute of Technology, Kharagpur Lecture - 21 Image Enhancement Frequency Domain Processing
More informationMarkov Random Fields and Gibbs Sampling for Image Denoising
Markov Random Fields and Gibbs Sampling for Image Denoising Chang Yue Electrical Engineering Stanford University changyue@stanfoed.edu Abstract This project applies Gibbs Sampling based on different Markov
More informationMultilevel Graph Partitioning
Multilevel Graph Partitioning George Karypis and Vipin Kumar Adapted from Jmes Demmel s slide (UC-Berkely 2009) and Wasim Mohiuddin (2011) Cover image from: Wang, Wanyi, et al. "Polygonal Clustering Analysis
More informationHarmonic Spline Series Representation of Scaling Functions
Harmonic Spline Series Representation of Scaling Functions Thierry Blu and Michael Unser Biomedical Imaging Group, STI/BIO-E, BM 4.34 Swiss Federal Institute of Technology, Lausanne CH-5 Lausanne-EPFL,
More informationGeometric Modeling in Graphics
Geometric Modeling in Graphics Part 10: Surface reconstruction Martin Samuelčík www.sccg.sk/~samuelcik samuelcik@sccg.sk Curve, surface reconstruction Finding compact connected orientable 2-manifold surface
More informationIntroduction to Machine Learning
Introduction to Machine Learning Clustering Varun Chandola Computer Science & Engineering State University of New York at Buffalo Buffalo, NY, USA chandola@buffalo.edu Chandola@UB CSE 474/574 1 / 19 Outline
More informationLecture 2.2 Cubic Splines
Lecture. Cubic Splines Cubic Spline The equation for a single parametric cubic spline segment is given by 4 i t Bit t t t i (..) where t and t are the parameter values at the beginning and end of the segment.
More informationSplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels Matthias Fey, Jan Eric Lenssen, Frank Weichert, Heinrich Müller Department of Computer Graphics TU Dortmund University {matthiasfey,janericlenssen}@udoedu
More informationDiscriminative Clustering for Image Co-Segmentation
Discriminative Clustering for Image Co-Segmentation Joulin, A.; Bach, F.; Ponce, J. (CVPR. 2010) Iretiayo Akinola Josh Tennefoss Outline Why Co-segmentation? Previous Work Problem Formulation Experimental
More informationNeural Network and Deep Learning. Donglin Zeng, Department of Biostatistics, University of North Carolina
Neural Network and Deep Learning Early history of deep learning Deep learning dates back to 1940s: known as cybernetics in the 1940s-60s, connectionism in the 1980s-90s, and under the current name starting
More informationData mining with sparse grids
Data mining with sparse grids Jochen Garcke and Michael Griebel Institut für Angewandte Mathematik Universität Bonn Data mining with sparse grids p.1/40 Overview What is Data mining? Regularization networks
More informationThis Talk. 1) Node embeddings. Map nodes to low-dimensional embeddings. 2) Graph neural networks. Deep learning architectures for graphstructured
Representation Learning on Networks, snap.stanford.edu/proj/embeddings-www, WWW 2018 1 This Talk 1) Node embeddings Map nodes to low-dimensional embeddings. 2) Graph neural networks Deep learning architectures
More informationSpectral Compression of Mesh Geometry
Spectral Compression of Mesh Geometry Zachi Karni, Craig Gotsman SIGGRAPH 2000 1 Introduction Thus far, topology coding drove geometry coding. Geometric data contains far more information (15 vs. 3 bits/vertex).
More informationSocial Network Analysis
Social Network Analysis Mathematics of Networks Manar Mohaisen Department of EEC Engineering Adjacency matrix Network types Edge list Adjacency list Graph representation 2 Adjacency matrix Adjacency matrix
More informationFundamentals of Digital Image Processing
\L\.6 Gw.i Fundamentals of Digital Image Processing A Practical Approach with Examples in Matlab Chris Solomon School of Physical Sciences, University of Kent, Canterbury, UK Toby Breckon School of Engineering,
More informationCS 179 Lecture 16. Logistic Regression & Parallel SGD
CS 179 Lecture 16 Logistic Regression & Parallel SGD 1 Outline logistic regression (stochastic) gradient descent parallelizing SGD for neural nets (with emphasis on Google s distributed neural net implementation)
More informationMy favorite application using eigenvalues: partitioning and community detection in social networks
My favorite application using eigenvalues: partitioning and community detection in social networks Will Hobbs February 17, 2013 Abstract Social networks are often organized into families, friendship groups,
More informationBeyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking Martin Danelljan, Andreas Robinson, Fahad Shahbaz Khan, Michael Felsberg 2 Discriminative Correlation Filters (DCF)
More informationKernighan/Lin - Preliminary Definitions. Comments on Kernighan/Lin Algorithm. Partitioning Without Nodal Coordinates Kernighan/Lin
Partitioning Without Nodal Coordinates Kernighan/Lin Given G = (N,E,W E ) and a partitioning N = A U B, where A = B. T = cost(a,b) = edge cut of A and B partitions. Find subsets X of A and Y of B with
More information1 Overview. 2 Applications of submodular maximization. AM 221: Advanced Optimization Spring 2016
AM : Advanced Optimization Spring 06 Prof. Yaron Singer Lecture 0 April th Overview Last time we saw the problem of Combinatorial Auctions and framed it as a submodular maximization problem under a partition
More informationTopics in Machine Learning
Topics in Machine Learning Gilad Lerman School of Mathematics University of Minnesota Text/slides stolen from G. James, D. Witten, T. Hastie, R. Tibshirani and A. Ng Machine Learning - Motivation Arthur
More informationGeodesics in heat: A new approach to computing distance
Geodesics in heat: A new approach to computing distance based on heat flow Diana Papyan Faculty of Informatics - Technische Universität München Abstract In this report we are going to introduce new method
More informationREPRESENTATION OF BIG DATA BY DIMENSION REDUCTION
Fundamental Journal of Mathematics and Mathematical Sciences Vol. 4, Issue 1, 2015, Pages 23-34 This paper is available online at http://www.frdint.com/ Published online November 29, 2015 REPRESENTATION
More informationCHAPTER 3 DIFFERENT DOMAINS OF WATERMARKING. domain. In spatial domain the watermark bits directly added to the pixels of the cover
38 CHAPTER 3 DIFFERENT DOMAINS OF WATERMARKING Digital image watermarking can be done in both spatial domain and transform domain. In spatial domain the watermark bits directly added to the pixels of the
More informationOff-the-Grid Compressive Imaging: Recovery of Piecewise Constant Images from Few Fourier Samples
Off-the-Grid Compressive Imaging: Recovery of Piecewise Constant Images from Few Fourier Samples Greg Ongie PhD Candidate Department of Applied Math and Computational Sciences University of Iowa April
More informationSome fast and compact neural network solutions for artificial intelligence applications
Some fast and compact neural network solutions for artificial intelligence applications Radu Dogaru, University Politehnica of Bucharest ETTI, Dept. of Applied Electronics and Info. Eng., Natural Computing
More informationInteractive Graphics. Lecture 9: Introduction to Spline Curves. Interactive Graphics Lecture 9: Slide 1
Interactive Graphics Lecture 9: Introduction to Spline Curves Interactive Graphics Lecture 9: Slide 1 Interactive Graphics Lecture 13: Slide 2 Splines The word spline comes from the ship building trade
More informationEvaluation of Loop Subdivision Surfaces
Evaluation of Loop Subdivision Surfaces Jos Stam Alias wavefront, Inc. 8 Third Ave, 8th Floor, Seattle, WA 980, U.S.A. jstam@aw.sgi.com Abstract This paper describes a technique to evaluate Loop subdivision
More informationImage Similarities for Learning Video Manifolds. Selen Atasoy MICCAI 2011 Tutorial
Image Similarities for Learning Video Manifolds Selen Atasoy MICCAI 2011 Tutorial Image Spaces Image Manifolds Tenenbaum2000 Roweis2000 Tenenbaum2000 [Tenenbaum2000: J. B. Tenenbaum, V. Silva, J. C. Langford:
More informationComputational Statistics and Mathematics for Cyber Security
and Mathematics for Cyber Security David J. Marchette Sept, 0 Acknowledgment: This work funded in part by the NSWC In-House Laboratory Independent Research (ILIR) program. NSWCDD-PN--00 Topics NSWCDD-PN--00
More informationConvolutional-Recursive Deep Learning for 3D Object Classification
Convolutional-Recursive Deep Learning for 3D Object Classification Richard Socher, Brody Huval, Bharath Bhat, Christopher D. Manning, Andrew Y. Ng NIPS 2012 Iro Armeni, Manik Dhar Motivation Hand-designed
More informationExperimental Data and Training
Modeling and Control of Dynamic Systems Experimental Data and Training Mihkel Pajusalu Alo Peets Tartu, 2008 1 Overview Experimental data Designing input signal Preparing data for modeling Training Criterion
More information2D Spline Curves. CS 4620 Lecture 18
2D Spline Curves CS 4620 Lecture 18 2014 Steve Marschner 1 Motivation: smoothness In many applications we need smooth shapes that is, without discontinuities So far we can make things with corners (lines,
More informationClustering With Multi-Layer Graphs: A Spectral Perspective
5820 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 60, NO. 11, NOVEMBER 2012 Clustering With Multi-Layer Graphs: A Spectral Perspective Xiaowen Dong, Pascal Frossard, Senior Member, IEEE, Pierre Vandergheynst,
More informationA Weighted Kernel PCA Approach to Graph-Based Image Segmentation
A Weighted Kernel PCA Approach to Graph-Based Image Segmentation Carlos Alzate Johan A. K. Suykens ESAT-SCD-SISTA Katholieke Universiteit Leuven Leuven, Belgium January 25, 2007 International Conference
More informationMATH 567: Mathematical Techniques in Data
Supervised and unsupervised learning Supervised learning problems: MATH 567: Mathematical Techniques in Data (X, Y ) P (X, Y ). Data Science Clustering I is labelled (input/output) with joint density We
More informationLecture 13 Segmentation and Scene Understanding Chris Choy, Ph.D. candidate Stanford Vision and Learning Lab (SVL)
Lecture 13 Segmentation and Scene Understanding Chris Choy, Ph.D. candidate Stanford Vision and Learning Lab (SVL) http://chrischoy.org Stanford CS231A 1 Understanding a Scene Objects Chairs, Cups, Tables,
More informationSocial-Network Graphs
Social-Network Graphs Mining Social Networks Facebook, Google+, Twitter Email Networks, Collaboration Networks Identify communities Similar to clustering Communities usually overlap Identify similarities
More informationTopological Inference via Meshing
Topological Inference via Meshing Don Sheehy Theory Lunch Joint work with Benoit Hudson, Gary Miller, and Steve Oudot Computer Scientists want to know the shape of data. Clustering Principal Component
More informationCHAPTER 4. ANALYSIS of GRAPH THEORETICAL IMAGE SEGMENTATION METHODS
CHAPTER 4 ANALYSIS of GRAPH THEORETICAL IMAGE SEGMENTATION METHODS 4.1 Introduction In Graph based methods image is represented by undirected weighted graph where the nodes are pixels or pixel regions.
More informationThe Un-normalized Graph p-laplacian based Semi-supervised Learning Method and Speech Recognition Problem
Int. J. Advance Soft Compu. Appl, Vol. 9, No. 1, March 2017 ISSN 2074-8523 The Un-normalized Graph p-laplacian based Semi-supervised Learning Method and Speech Recognition Problem Loc Tran 1 and Linh Tran
More informationAn Efficient, Geometric Multigrid Solver for the Anisotropic Diffusion Equation in Two and Three Dimensions
1 n Efficient, Geometric Multigrid Solver for the nisotropic Diffusion Equation in Two and Three Dimensions Tolga Tasdizen, Ross Whitaker UUSCI-2004-002 Scientific Computing and Imaging Institute University
More informationNeural Network Optimization and Tuning / Spring 2018 / Recitation 3
Neural Network Optimization and Tuning 11-785 / Spring 2018 / Recitation 3 1 Logistics You will work through a Jupyter notebook that contains sample and starter code with explanations and comments throughout.
More informationInception and Residual Networks. Hantao Zhang. Deep Learning with Python.
Inception and Residual Networks Hantao Zhang Deep Learning with Python https://en.wikipedia.org/wiki/residual_neural_network Deep Neural Network Progress from Large Scale Visual Recognition Challenge (ILSVRC)
More informationUnsupervised Learning of Spatiotemporally Coherent Metrics
Unsupervised Learning of Spatiotemporally Coherent Metrics Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun arxiv 2015. Presented by Jackie Chu Contributions Insight between slow feature
More informationBabu Madhav Institute of Information Technology Years Integrated M.Sc.(IT)(Semester - 7)
5 Years Integrated M.Sc.(IT)(Semester - 7) 060010707 Digital Image Processing UNIT 1 Introduction to Image Processing Q: 1 Answer in short. 1. What is digital image? 1. Define pixel or picture element?
More informationClustering algorithms and introduction to persistent homology
Foundations of Geometric Methods in Data Analysis 2017-18 Clustering algorithms and introduction to persistent homology Frédéric Chazal INRIA Saclay - Ile-de-France frederic.chazal@inria.fr Introduction
More informationCS7540 Spectral Algorithms, Spring 2017 Lecture #2. Matrix Tree Theorem. Presenter: Richard Peng Jan 12, 2017
CS7540 Spectral Algorithms, Spring 2017 Lecture #2 Matrix Tree Theorem Presenter: Richard Peng Jan 12, 2017 DISCLAIMER: These notes are not necessarily an accurate representation of what I said during
More informationParallelization in the Big Data Regime: Model Parallelization? Sham M. Kakade
Parallelization in the Big Data Regime: Model Parallelization? Sham M. Kakade Machine Learning for Big Data CSE547/STAT548 University of Washington S. M. Kakade (UW) Optimization for Big data 1 / 12 Announcements...
More informationContrast adjustment via Bayesian sequential partitioning
Contrast adjustment via Bayesian sequential partitioning Zhiyu Wang, Shuo Xie, Bai Jiang Abstract Photographs taken in dim light have low color contrast. However, traditional methods for adjusting contrast
More informationPoints Lines Connected points X-Y Scatter. X-Y Matrix Star Plot Histogram Box Plot. Bar Group Bar Stacked H-Bar Grouped H-Bar Stacked
Plotting Menu: QCExpert Plotting Module graphs offers various tools for visualization of uni- and multivariate data. Settings and options in different types of graphs allow for modifications and customizations
More informationInternational Journal of Advanced Research in Computer Science and Software Engineering
Volume 2, Issue 10, October 2012 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A New Efficient
More information