Collabora've Filtering
|
|
|
- Nora Waters
- 5 years ago
- Views:
Transcription
1 Collabora've Filtering EECS 349 Machine Learning Bongjun Kim Fall, 2015
2 What is CollaboraCve Filtering? RecommendaCon system Amazon recommends items based on your purchase history and racngs RecommendaCon Purchase history
3 What is CollaboraCve Filtering? RecommendaCon system Amazon recommends items based on your purchase history and racngs View history RecommendaCon
4 What is CollaboraCve Filtering? Task: How do I predict what you ll like? Two approaches User- based: You will like item A because users who are similar to you like item A. Item- based: You will like item A because you like items that are similar to item A.
5 User- Based CollaboraCve Filtering Find users that is similar to you and you might like the item the user likes A I like.. - Star wars - Star Trek - Mission Impossible B I like.. - Star wars - Star Trek - Mission Impossible - X- men B is a user who has similar preference to A. So A would like X- men too!!
6 Item- Based CollaboraCve Filtering You might like items that are similar to items you already like A I like Star wars! Star Trek is a movie similar to Star Wars because it has star in the name. Then, A would like Star Trek too! Do you think A would also like Dancing with the Star?
7 Feature SelecCon Measuring similarity (of users or items) requires measuring their features. Which features should I measure? Are there features that are (relacvely) insensicve to the parcculars of the recommendacon tasks? User racngs to items or their purchase history is one of the explicit features to measure user preference
8 USER- BASED COLLABORATIVE FILTERING
9 How do we find a user who is similar? Distance (or similarity) measure N- dimensional space Example: movie racngs of 3 users RaCngs from 1 (dislike) to 5 (like) Harry Poaer Star Wars U1 U2 U Harry poaer U1 U Star wars U2
10 Which similarity measure to use? p- norm Manhaaan Euclidian Pearson CorrelaCon Cosine Similarity Etc..
11 Who is the most similar to John? Example #1 IncepCon Begin again Once Brian Bob Cathy John Manhaaan Distance: (John, Brian) = =1 (John, Bob) = =9 (John, Cathy) = = 6 Q: Does Manhaaan Distance measure similarices properly in this data set?
12 Who is the most similar to Adam? Example #2 IncepCon Begin again Once Star wars Bill Brian Adam Manhaaan Distance: (Adam, Bill) = =4 (Adam, Brian) = = 6 Q: Does Manhaaan Distance measure similarices properly in this data set? Different users may use different racng scales
13 Who is the most similar to Adam? Bill Brian Adam 1 0 IncepCon Begin again Once Star wars - Manhaaan Distance: (Adam, Bill) = =4 (Adam, Brian) = = 6 Q: Does Manhaaan Distance measure similarices properly in this data set? Different users may use different racng scales
14 Pearson CorrelaCon Measure of correlacon between two variables Pearson correlacon coefficient Range (- 1, 1) A perfect posicve correlacon: 1 A perfect negacve correlacon: - 1, ) ( ) ( ) )( ( ), ( 2, 2,,, = C i i C i i C i i i r r r r r r r r sim v v u u v v u u v u In Python, >> import scipy.stats >> scipy.stats.pearsonr(array1, array2)
15 Cosine Similarity Measure of similarity between two vectors Range from - 1 (opposite) to 1 (same) Cosine similarity between vector a and b: sim(a, b) = a b a b
16 Who is the most similar to Adam? Example #2 IncepCon Begin again Once Star wars Bill Brian Adam Pearson CorrelaCon: (Adam, Bill) = - 1 (Adam, Brian) = 1 Q: Does Pearson CorrelaCon measure similarices properly in this data set?
17 How to predict racngs to unrated items User- based K- Nearest Neighbor CollaboraCve Filtering 1) Define a similarity measure 2) Pick k users that had similar preferences to those of current user 3) Compute a prediccon from a weighted average of k nearest neighbors racngs (see the next slide) You need to do experiments to find opkmal k value.
18 How to predict racngs to unrated items PredicCon for the racng of user a for item p. RaCng of user b for item p pred(a, p) = r a + b k sim(a, b) ( r r ) b, p b sim(a, b) b k User a s average racng Similarity between user a and user b
19 Let s praccce user- based k- NN CF In this praccce and our homework, we will use much simpler way to compute a prediccon of racng 1) Define a similarity measure 2) Pick k users that had similar preferences to those of current user 3) Pick the mode of the top k nearest neighbors as the predicted ra'ng - ex) If you pick 3 neighbors and their ra'ngs to the target item are (2, 2, 3), then the predic'on will be 2.
20 PracCce: User- based k- NN CF (k=1) Example #1: How would John rate Star wars? IncepCon Begin again Once Star wars Brian Bob Cathy John 5 1 2? Manhaaan Distance: (John, Brian) = =1 (John, Bob) = =9 (John, Cathy) = = 6 The nearest neighbor: Brian John s racng to Star wars: 4
21 PracCce: User- based k- NN CF (k=1) Example #2: How would John rate Avatar? IncepCon Begin again Once Star wars Avatar Brian Bob Cathy John ? Manhaaan Distance: (John, Brian) = =5 (John, Bob) = = 6 (John, Cathy) = = 4 The nearest neighbor: Cathy John s racng to Avatar: 1 Pearson CorrelaCon Coefficient (John, Brian) = (John, Bob) = 1.0 (John, Cathy) = 0.95 The nearest neighbor: Bob John s racng to Avatar: 2
22 ITEM- BASED COLLABORATIVE FILTERING
23 How to predict racngs to unrated items Item- based K- Nearest Neighbor CollaboraCve Filtering 1) Define a similarity measure between items 2) Pick k items rated by the current user similar to the target item 3) Compute a prediccon from a weighted average of the k similar items racngs
24 Let s praccce item- based k- NN CF In this praccce and our homework, we will use much simpler way to compute a prediccon of racng 1) Define a similarity measure between items 2) Pick k items rated by the current user similar to the target item 3) Pick the mode of the top k nearest neighbors as the predicted ra'ng - ex) If you picked 3 items and current user s ra'ngs to the 3 items are (2, 2, 3), then the predic'on will be 2.
25 PracCce: Item- based k- NN CF (k=1) Example #1 IncepCon Begin again Once Star wars Brian Bob Cathy John 5 1 2? Manhaaan Distance: (Star wars, IncepCon) = =3 (Star wars, Begin again) = =5 (Star wars, Once) = = 6 The most similar item to Star wars: IncepCon John s racng to Star wars: 5
26 The Cold Start Problem What if this user has never rated anything before? What if nobody has rated this item before? AddiConal informacon. For example, Ask users to rate some inical items Demographic informacon for users Content analysis or metadata for items
27 Missing values Missing values in user- racng matrix What if two users have rated different sets of things? How do we compare them? What if two items have been rated by disjoint sets of users? How do we compare them?
28 Dealing with missing values Example IncepCon Begin again Once Star wars Avatar Brian 2? 3? 4 Bob Cathy 5? John 5? 2 3?
29 Dealing with missing values Example IncepCon Begin again Once Star wars Avatar Brian Bob Cathy John ?
30 Dealing with missing values Discarding the person/item from comparison? It does not solve cold start problem What if the data set is so sparse? Pulng in a crazy number (- 1000) for missing values? Pulng in a random number? Pulng in a mean (median) value? Mean value of what set? Other advanced imputacon technique?
31 Make a decision Which similarity (or distance) measure to use? How many neighbors to pick? How to weight neighbors chosen? User- based or item- based? How to deal with missing values?
Collaborative Filtering
Collaborative Filtering Nicholas Ruozzi University of Texas at Dallas based on the slides of Alex Smola & Narges Razavian Collaborative Filtering Combining information among collaborating entities to make
CS425: Algorithms for Web Scale Data
CS: Algorithms for Web Scale Data Most of the slides are from the Mining of Massive Datasets book. These slides have been modified for CS. The original slides can be accessed at: www.mmds.org Customer
Collaborative Filtering. Radek Pelánek
Collaborative Filtering Radek Pelánek 2017 Notes on Lecture the most technical lecture of the course includes some scary looking math, but typically with intuitive interpretation use of standard machine
Recommendation Systems
Recommendation Systems Collaborative Filtering Finding somebody or something similar by looking at recommendation systems Recommendation systems are found everywhere example: Amazon Recommendation systems
Preliminaries. Data Mining. The art of extracting knowledge from large bodies of structured data. Let s put it to use!
Data Mining The art of extracting knowledge from large bodies of structured data. Let s put it to use! 1 Recommendations 2 Basic Recommendations with Collaborative Filtering Making Recommendations 4 The
Matrix Factorization and Collaborative Filtering
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Matrix Factorization and Collaborative Filtering MF Readings: (Koren et al., 2009)
Generative Models for Discrete Data
Generative Models for Discrete Data ddebarr@uw.edu 2016-04-21 Agenda Bayesian Concept Learning Beta-Binomial Model Dirichlet-Multinomial Model Naïve Bayes Classifiers Bayesian Concept Learning Numbers
Recommendation Systems
Recommendation Systems Pawan Goyal CSE, IITKGP October 21, 2014 Pawan Goyal (IIT Kharagpur) Recommendation Systems October 21, 2014 1 / 52 Recommendation System? Pawan Goyal (IIT Kharagpur) Recommendation
Collaborative Topic Modeling for Recommending Scientific Articles
Collaborative Topic Modeling for Recommending Scientific Articles Chong Wang and David M. Blei Best student paper award at KDD 2011 Computer Science Department, Princeton University Presented by Tian Cao
Recommendation Systems
Recommendation Systems Pawan Goyal CSE, IITKGP October 29-30, 2015 Pawan Goyal (IIT Kharagpur) Recommendation Systems October 29-30, 2015 1 / 61 Recommendation System? Pawan Goyal (IIT Kharagpur) Recommendation
Andriy Mnih and Ruslan Salakhutdinov
MATRIX FACTORIZATION METHODS FOR COLLABORATIVE FILTERING Andriy Mnih and Ruslan Salakhutdinov University of Toronto, Machine Learning Group 1 What is collaborative filtering? The goal of collaborative
Data Science Mastery Program
Data Science Mastery Program Copyright Policy All content included on the Site or third-party platforms as part of the class, such as text, graphics, logos, button icons, images, audio clips, video clips,
ELEC6910Q Analytics and Systems for Social Media and Big Data Applications Lecture 3 Centrality, Similarity, and Strength Ties
ELEC6910Q Analytics and Systems for Social Media and Big Data Applications Lecture 3 Centrality, Similarity, and Strength Ties Prof. James She james.she@ust.hk 1 Last lecture 2 Selected works from Tutorial
* Matrix Factorization and Recommendation Systems
Matrix Factorization and Recommendation Systems Originally presented at HLF Workshop on Matrix Factorization with Loren Anderson (University of Minnesota Twin Cities) on 25 th September, 2017 15 th March,
CS249: ADVANCED DATA MINING
CS249: ADVANCED DATA MINING Recommender Systems Instructor: Yizhou Sun yzsun@cs.ucla.edu May 17, 2017 Methods Learnt: Last Lecture Classification Clustering Vector Data Text Data Recommender System Decision
Probabilistic Matrix Factorization
Probabilistic Matrix Factorization David M. Blei Columbia University November 25, 2015 1 Dyadic data One important type of modern data is dyadic data. Dyadic data are measurements on pairs. The idea is
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
Similarity and recommender systems
Similarity and recommender systems Hiroshi Shimodaira January-March 208 In this chapter we shall look at how to measure the similarity between items To be precise we ll look at a measure of the dissimilarity
MIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October,
MIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October, 23 2013 The exam is closed book. You are allowed a one-page cheat sheet. Answer the questions in the spaces provided on the question sheets. If you run
Introduction to Logistic Regression
Introduction to Logistic Regression Guy Lebanon Binary Classification Binary classification is the most basic task in machine learning, and yet the most frequent. Binary classifiers often serve as the
Recommendation Systems
Recommendation Systems Popularity Recommendation Systems Predicting user responses to options Offering news articles based on users interests Offering suggestions on what the user might like to buy/consume
Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen. Recommendation. Tobias Scheffer
Universität Potsdam Institut für Informatik Lehrstuhl Maschinelles Lernen Recommendation Tobias Scheffer Recommendation Engines Recommendation of products, music, contacts,.. Based on user features, item
Large-Scale Matrix Factorization with Distributed Stochastic Gradient Descent
Large-Scale Matrix Factorization with Distributed Stochastic Gradient Descent KDD 2011 Rainer Gemulla, Peter J. Haas, Erik Nijkamp and Yannis Sismanis Presenter: Jiawen Yao Dept. CSE, UT Arlington 1 1
Collaborative Filtering Matrix Completion Alternating Least Squares
Case Study 4: Collaborative Filtering Collaborative Filtering Matrix Completion Alternating Least Squares Machine Learning for Big Data CSE547/STAT548, University of Washington Sham Kakade May 19, 2016
Collaborative Filtering: A Machine Learning Perspective
Collaborative Filtering: A Machine Learning Perspective Chapter 6: Dimensionality Reduction Benjamin Marlin Presenter: Chaitanya Desai Collaborative Filtering: A Machine Learning Perspective p.1/18 Topics
Machine Learning Basics
Security and Fairness of Deep Learning Machine Learning Basics Anupam Datta CMU Spring 2019 Image Classification Image Classification Image classification pipeline Input: A training set of N images, each
Recommender Systems. Dipanjan Das Language Technologies Institute Carnegie Mellon University. 20 November, 2007
Recommender Systems Dipanjan Das Language Technologies Institute Carnegie Mellon University 20 November, 2007 Today s Outline What are Recommender Systems? Two approaches Content Based Methods Collaborative
Data Mining Techniques
Data Mining Techniques CS 622 - Section 2 - Spring 27 Pre-final Review Jan-Willem van de Meent Feedback Feedback https://goo.gl/er7eo8 (also posted on Piazza) Also, please fill out your TRACE evaluations!
Probabilistic Partial User Model Similarity for Collaborative Filtering
Probabilistic Partial User Model Similarity for Collaborative Filtering Amancio Bouza, Gerald Reif, Abraham Bernstein Department of Informatics, University of Zurich {bouza,reif,bernstein}@ifi.uzh.ch Abstract.
Techniques for Dimensionality Reduction. PCA and Other Matrix Factorization Methods
Techniques for Dimensionality Reduction PCA and Other Matrix Factorization Methods Outline Principle Compoments Analysis (PCA) Example (Bishop, ch 12) PCA as a mixture model variant With a continuous latent
Recommender Systems: Overview and. Package rectools. Norm Matloff. Dept. of Computer Science. University of California at Davis.
Recommender December 13, 2016 What Are Recommender Systems? What Are Recommender Systems? Various forms, but here is a common one, say for data on movie ratings: What Are Recommender Systems? Various forms,
Part 1: You are given the following system of two equations: x + 2y = 16 3x 4y = 2
Solving Systems of Equations Algebraically Teacher Notes Comment: As students solve equations throughout this task, have them continue to explain each step using properties of operations or properties
Correlation and regression
NST 1B Experimental Psychology Statistics practical 1 Correlation and regression Rudolf Cardinal & Mike Aitken 11 / 12 November 2003 Department of Experimental Psychology University of Cambridge Handouts:
Binary Principal Component Analysis in the Netflix Collaborative Filtering Task
Binary Principal Component Analysis in the Netflix Collaborative Filtering Task László Kozma, Alexander Ilin, Tapani Raiko first.last@tkk.fi Helsinki University of Technology Adaptive Informatics Research
EECS 349:Machine Learning Bryan Pardo
EECS 349:Machine Learning Bryan Pardo Topic 2: Decision Trees (Includes content provided by: Russel & Norvig, D. Downie, P. Domingos) 1 General Learning Task There is a set of possible examples Each example
CSE 494/598 Lecture-4: Correlation Analysis. **Content adapted from last year s slides
CSE 494/598 Lecture-4: Correlation Analysis LYDIA MANIKONDA HT TP://WWW.PUBLIC.ASU.EDU/~LMANIKON / **Content adapted from last year s slides Announcements Project-1 Due: February 12 th 2016 Analysis report:
Similarity Search. Stony Brook University CSE545, Fall 2016
Similarity Search Stony Brook University CSE545, Fall 20 Finding Similar Items Applications Document Similarity: Mirrored web-pages Plagiarism; Similar News Recommendations: Online purchases Movie ratings
Matrix Factorization Techniques for Recommender Systems
Matrix Factorization Techniques for Recommender Systems Patrick Seemann, December 16 th, 2014 16.12.2014 Fachbereich Informatik Recommender Systems Seminar Patrick Seemann Topics Intro New-User / New-Item
LINEAR ALGEBRA KNOWLEDGE SURVEY
LINEAR ALGEBRA KNOWLEDGE SURVEY Instructions: This is a Knowledge Survey. For this assignment, I am only interested in your level of confidence about your ability to do the tasks on the following pages.
Mining of Massive Datasets Jure Leskovec, AnandRajaraman, Jeff Ullman Stanford University
Note to other teachers and users of these slides: We would be delighted if you found this our material useful in giving your own lectures. Feel free to use these slides verbatim, or to modify them to fit
High-Dimensional Indexing by Distributed Aggregation
High-Dimensional Indexing by Distributed Aggregation Yufei Tao ITEE University of Queensland In this lecture, we will learn a new approach for indexing high-dimensional points. The approach borrows ideas
smart reply and implicit semantics Matthew Henderson and Brian Strope Google AI
smart reply and implicit semantics Matthew Henderson and Brian Strope Google AI collaborators include: Rami Al-Rfou, Yun-hsuan Sung Laszlo Lukacs, Ruiqi Guo, Sanjiv Kumar Balint Miklos, Ray Kurzweil and
Geometric View of Machine Learning Nearest Neighbor Classification. Slides adapted from Prof. Carpuat
Geometric View of Machine Learning Nearest Neighbor Classification Slides adapted from Prof. Carpuat What we know so far Decision Trees What is a decision tree, and how to induce it from data Fundamental
High Dimensional Geometry, Curse of Dimensionality, Dimension Reduction
Chapter 11 High Dimensional Geometry, Curse of Dimensionality, Dimension Reduction High-dimensional vectors are ubiquitous in applications (gene expression data, set of movies watched by Netflix customer,
Recommender Systems EE448, Big Data Mining, Lecture 10. Weinan Zhang Shanghai Jiao Tong University
2018 EE448, Big Data Mining, Lecture 10 Recommender Systems Weinan Zhang Shanghai Jiao Tong University http://wnzhang.net http://wnzhang.net/teaching/ee448/index.html Content of This Course Overview of
MATH 118 FINAL EXAM STUDY GUIDE
MATH 118 FINAL EXAM STUDY GUIDE Recommendations: 1. Take the Final Practice Exam and take note of questions 2. Use this study guide as you take the tests and cross off what you know well 3. Take the Practice
Physics 2020 Lab 5 Intro to Circuits
Physics 2020 Lab 5 Intro to Circuits Name Section Tues Wed Thu 8am 10am 12pm 2pm 4pm Introduction In this lab, we will be using The Circuit Construction Kit (CCK). CCK is a computer simulation that allows
Missing Data and Dynamical Systems
U NIVERSITY OF ILLINOIS AT URBANA-CHAMPAIGN CS598PS Machine Learning for Signal Processing Missing Data and Dynamical Systems 12 October 2017 Today s lecture Dealing with missing data Tracking and linear
CH 59 SQUARE ROOTS. Every positive number has two square roots. Ch 59 Square Roots. Introduction
59 CH 59 SQUARE ROOTS Introduction W e saw square roots when we studied the Pythagorean Theorem. They may have been hidden, but when the end of a right-triangle problem resulted in an equation like c =
a Short Introduction
Collaborative Filtering in Recommender Systems: a Short Introduction Norm Matloff Dept. of Computer Science University of California, Davis matloff@cs.ucdavis.edu December 3, 2016 Abstract There is a strong
Dimension Reduction. David M. Blei. April 23, 2012
Dimension Reduction David M. Blei April 23, 2012 1 Basic idea Goal: Compute a reduced representation of data from p -dimensional to q-dimensional, where q < p. x 1,...,x p z 1,...,z q (1) We want to do
Decision Trees. Nicholas Ruozzi University of Texas at Dallas. Based on the slides of Vibhav Gogate and David Sontag
Decision Trees Nicholas Ruozzi University of Texas at Dallas Based on the slides of Vibhav Gogate and David Sontag Supervised Learning Input: labelled training data i.e., data plus desired output Assumption:
CS Homework 3. October 15, 2009
CS 294 - Homework 3 October 15, 2009 If you have questions, contact Alexandre Bouchard (bouchard@cs.berkeley.edu) for part 1 and Alex Simma (asimma@eecs.berkeley.edu) for part 2. Also check the class website
Recommender Systems. From Content to Latent Factor Analysis. Michael Hahsler
Recommender Systems From Content to Latent Factor Analysis Michael Hahsler Intelligent Data Analysis Lab (IDA@SMU) CSE Department, Lyle School of Engineering Southern Methodist University CSE Seminar September
PS2.1 & 2.2: Linear Correlations PS2: Bivariate Statistics
PS2.1 & 2.2: Linear Correlations PS2: Bivariate Statistics LT1: Basics of Correlation LT2: Measuring Correlation and Line of best fit by eye Univariate (one variable) Displays Frequency tables Bar graphs
From Non-Negative Matrix Factorization to Deep Learning
The Math!! From Non-Negative Matrix Factorization to Deep Learning Intuitions and some Math too! luissarmento@gmailcom https://wwwlinkedincom/in/luissarmento/ October 18, 2017 The Math!! Introduction Disclaimer
California Content Standard. Essentials for Algebra (lesson.exercise) of Test Items. Grade 6 Statistics, Data Analysis, & Probability.
California Content Standard Grade 6 Statistics, Data Analysis, & Probability 1. Students compute & analyze statistical measurements for data sets: 1.1 Compute the mean, median & mode of data sets 1.2 Understand
CS155: Probability and Computing: Randomized Algorithms and Probabilistic Analysis
CS155: Probability and Computing: Randomized Algorithms and Probabilistic Analysis Eli Upfal Eli Upfal@brown.edu Office: 319 TA s: Lorenzo De Stefani and Sorin Vatasoiu cs155tas@cs.brown.edu It is remarkable
Collaborative topic models: motivations cont
Collaborative topic models: motivations cont Two topics: machine learning social network analysis Two people: " boy Two articles: article A! girl article B Preferences: The boy likes A and B --- no problem.
Scaling Neighbourhood Methods
Quick Recap Scaling Neighbourhood Methods Collaborative Filtering m = #items n = #users Complexity : m * m * n Comparative Scale of Signals ~50 M users ~25 M items Explicit Ratings ~ O(1M) (1 per billion)
Irreversible Processes
Irreversible Processes Examples: Block sliding on table comes to rest due to friction: KE converted to heat. Heat flows from hot object to cold object. Air flows into an evacuated chamber. Reverse process
Jeffrey D. Ullman Stanford University
Jeffrey D. Ullman Stanford University 2 Often, our data can be represented by an m-by-n matrix. And this matrix can be closely approximated by the product of two matrices that share a small common dimension
CS 6375 Machine Learning
CS 6375 Machine Learning Nicholas Ruozzi University of Texas at Dallas Slides adapted from David Sontag and Vibhav Gogate Course Info. Instructor: Nicholas Ruozzi Office: ECSS 3.409 Office hours: Tues.
PROBLEM SET 3: PROOF TECHNIQUES
PROBLEM SET 3: PROOF TECHNIQUES CS 198-087: INTRODUCTION TO MATHEMATICAL THINKING UC BERKELEY EECS FALL 2018 This homework is due on Monday, September 24th, at 6:30PM, on Gradescope. As usual, this homework
If we square the square root of something (that s not negative), we get the something : ( 34) ( ) 34
CH 60 MORE PYTHAGOREAN THEOREM AND MORE RADICALS Introduction T he last time we studied the Pythagorean Theorem we may have used our calculator to round square roots that didn t come out whole numbers.
Modeling User Rating Profiles For Collaborative Filtering
Modeling User Rating Profiles For Collaborative Filtering Benjamin Marlin Department of Computer Science University of Toronto Toronto, ON, M5S 3H5, CANADA marlin@cs.toronto.edu Abstract In this paper
Data Mining Recitation Notes Week 3
Data Mining Recitation Notes Week 3 Jack Rae January 28, 2013 1 Information Retrieval Given a set of documents, pull the (k) most similar document(s) to a given query. 1.1 Setup Say we have D documents
Predicting the Performance of Collaborative Filtering Algorithms
Predicting the Performance of Collaborative Filtering Algorithms Pawel Matuszyk and Myra Spiliopoulou Knowledge Management and Discovery Otto-von-Guericke University Magdeburg, Germany 04. June 2014 Pawel
Collaborative Filtering
Case Study 4: Collaborative Filtering Collaborative Filtering Matrix Completion Alternating Least Squares Machine Learning/Statistics for Big Data CSE599C1/STAT592, University of Washington Carlos Guestrin
Lecture 2: Linear regression
Lecture 2: Linear regression Roger Grosse 1 Introduction Let s ump right in and look at our first machine learning algorithm, linear regression. In regression, we are interested in predicting a scalar-valued
Designing Information Devices and Systems II Spring 2017 Murat Arcak and Michel Maharbiz Homework 9
EECS 16B Designing Information Devices and Systems II Spring 2017 Murat Arcak and Michel Maharbiz Homework 9 This homework is due April 5, 2017, at 17:00. 1. Midterm 2 - Question 1 Redo the midterm! 2.
Estimation of the Click Volume by Large Scale Regression Analysis May 15, / 50
Estimation of the Click Volume by Large Scale Regression Analysis Yuri Lifshits, Dirk Nowotka [International Computer Science Symposium in Russia 07, Ekaterinburg] Presented by: Aditya Menon UCSD May 15,
GRE Workshop Quantitative Reasoning. February 13 and 20, 2018
GRE Workshop Quantitative Reasoning February 13 and 20, 2018 Overview Welcome and introduction Tonight: arithmetic and algebra 6-7:15 arithmetic 7:15 break 7:30-8:45 algebra Time permitting, we ll start
MATHS Level 4+ Course Pupil Learning Log
Success is 99% Perspiration and % Inspiration St Ninian s High School Hard Work beats Talent every time when Talent doesn t Work Hard MATHS Level + Course Pupil Learning Log Expect to get out what you
Introduction to Optimization
Introduction to Optimization Konstantin Tretyakov (kt@ut.ee) MTAT.03.227 Machine Learning So far Machine learning is important and interesting The general concept: Fitting models to data So far Machine
Midterm Exam 1 Solution
EECS 126 Probability and Random Processes University of California, Berkeley: Fall 2015 Kannan Ramchandran September 22, 2015 Midterm Exam 1 Solution Last name First name SID Name of student on your left:
Probabilistic Neighborhood Selection in Collaborative Filtering Systems
Probabilistic Neighborhood Selection in Collaborative Filtering Systems Panagiotis Adamopoulos and Alexander Tuzhilin Department of Information, Operations and Management Sciences Leonard N. Stern School
CS 175: Project in Artificial Intelligence. Slides 4: Collaborative Filtering
CS 175: Project in Artificial Intelligence Slides 4: Collaborative Filtering 1 Topic 6: Collaborative Filtering Some slides taken from Prof. Smyth (with slight modifications) 2 Outline General aspects
Designing Information Devices and Systems I Fall 2018 Lecture Notes Note Positioning Sytems: Trilateration and Correlation
EECS 6A Designing Information Devices and Systems I Fall 08 Lecture Notes Note. Positioning Sytems: Trilateration and Correlation In this note, we ll introduce two concepts that are critical in our positioning
15-451/651: Design & Analysis of Algorithms September 13, 2018 Lecture #6: Streaming Algorithms last changed: August 30, 2018
15-451/651: Design & Analysis of Algorithms September 13, 2018 Lecture #6: Streaming Algorithms last changed: August 30, 2018 Today we ll talk about a topic that is both very old (as far as computer science
N/4 + N/2 + N = 2N 2.
CS61B Summer 2006 Instructor: Erin Korber Lecture 24, 7 Aug. 1 Amortized Analysis For some of the data structures we ve discussed (namely hash tables and splay trees), it was claimed that the average time
PATTERN RECOGNITION AND MACHINE LEARNING
PATTERN RECOGNITION AND MACHINE LEARNING Slide Set 3: Detection Theory January 2018 Heikki Huttunen heikki.huttunen@tut.fi Department of Signal Processing Tampere University of Technology Detection theory
The Lopsided Lovász Local Lemma
Department of Mathematics Nebraska Wesleyan University With Linyuan Lu and László Székely, University of South Carolina Note on Probability Spaces For this talk, every a probability space Ω is assumed
Point-of-Interest Recommendations: Learning Potential Check-ins from Friends
Point-of-Interest Recommendations: Learning Potential Check-ins from Friends Huayu Li, Yong Ge +, Richang Hong, Hengshu Zhu University of North Carolina at Charlotte + University of Arizona Hefei University
1 Machine Learning Concepts (16 points)
CSCI 567 Fall 2018 Midterm Exam DO NOT OPEN EXAM UNTIL INSTRUCTED TO DO SO PLEASE TURN OFF ALL CELL PHONES Problem 1 2 3 4 5 6 Total Max 16 10 16 42 24 12 120 Points Please read the following instructions
Take the Anxiety Out of Word Problems
Take the Anxiety Out of Word Problems I find that students fear any problem that has words in it. This does not have to be the case. In this chapter, we will practice a strategy for approaching word problems
Machine Learning. Measuring Distance. several slides from Bryan Pardo
Machine Learning Measuring Distance several slides from Bran Pardo 1 Wh measure distance? Nearest neighbor requires a distance measure Also: Local search methods require a measure of localit (Frida) Clustering
Machine Learning. Boris
Machine Learning Boris Nadion boris@astrails.com @borisnadion @borisnadion boris@astrails.com astrails http://astrails.com awesome web and mobile apps since 2005 terms AI (artificial intelligence)
Key Point. The nth order linear homogeneous equation with constant coefficients
General Solutions of Higher-Order Linear Equations In section 3.1, we saw the following fact: Key Point. The nth order linear homogeneous equation with constant coefficients a n y (n) +... + a 2 y + a
19. TAYLOR SERIES AND TECHNIQUES
19. TAYLOR SERIES AND TECHNIQUES Taylor polynomials can be generated for a given function through a certain linear combination of its derivatives. The idea is that we can approximate a function by a polynomial,
Ad Placement Strategies
Case Study 1: Estimating Click Probabilities Tackling an Unknown Number of Features with Sketching Machine Learning for Big Data CSE547/STAT548, University of Washington Emily Fox 2014 Emily Fox January
Large-scale Ordinal Collaborative Filtering
Large-scale Ordinal Collaborative Filtering Ulrich Paquet, Blaise Thomson, and Ole Winther Microsoft Research Cambridge, University of Cambridge, Technical University of Denmark ulripa@microsoft.com,brmt2@cam.ac.uk,owi@imm.dtu.dk
Online Dictionary Learning with Group Structure Inducing Norms
Online Dictionary Learning with Group Structure Inducing Norms Zoltán Szabó 1, Barnabás Póczos 2, András Lőrincz 1 1 Eötvös Loránd University, Budapest, Hungary 2 Carnegie Mellon University, Pittsburgh,
BIOINF 4120 Bioinforma2cs 2 - Structures and Systems -
BIOINF 4120 Bioinforma2cs 2 - Structures and Systems - Oliver Kohlbacher Summer 2014 3. RNA Structure Part II Overview RNA Folding Free energy as a criterion Folding free energy of RNA Zuker- SCegler algorithm
Selection and Adversary Arguments. COMP 215 Lecture 19
Selection and Adversary Arguments COMP 215 Lecture 19 Selection Problems We want to find the k'th largest entry in an unsorted array. Could be the largest, smallest, median, etc. Ideas for an n lg n algorithm?
NUMERICAL SOLUTION OF THE 1- D DIFFUSION EQUATION (39)
4/4/15 NUMERICAL SOLUTION OF THE 1- D DIFFUSION EQUATION (39) I Main Topics A MoCvaCon for using a numerical technique B Non- dimensionalizing the diffusion (heat flow) equacon C Finite- difference solucon
Data Mining Prof. Pabitra Mitra Department of Computer Science & Engineering Indian Institute of Technology, Kharagpur
Data Mining Prof. Pabitra Mitra Department of Computer Science & Engineering Indian Institute of Technology, Kharagpur Lecture 21 K - Nearest Neighbor V In this lecture we discuss; how do we evaluate the
Notes. Combinatorics. Combinatorics II. Notes. Notes. Slides by Christopher M. Bourke Instructor: Berthe Y. Choueiry. Spring 2006
Combinatorics Slides by Christopher M. Bourke Instructor: Berthe Y. Choueiry Spring 2006 Computer Science & Engineering 235 Introduction to Discrete Mathematics Sections 4.1-4.6 & 6.5-6.6 of Rosen cse235@cse.unl.edu
Tufts COMP 135: Introduction to Machine Learning
Tufts COMP 135: Introduction to Machine Learning https://www.cs.tufts.edu/comp/135/2019s/ Logistic Regression Many slides attributable to: Prof. Mike Hughes Erik Sudderth (UCI) Finale Doshi-Velez (Harvard)
Homework 1 Solutions Probability, Maximum Likelihood Estimation (MLE), Bayes Rule, knn
Homework 1 Solutions Probability, Maximum Likelihood Estimation (MLE), Bayes Rule, knn CMU 10-701: Machine Learning (Fall 2016) https://piazza.com/class/is95mzbrvpn63d OUT: September 13th DUE: September