Single category classification

Slides:



Advertisements
Similar presentations
Classification Classification Examples
Advertisements

Conceptual Clustering
Naive Bayes Classifiers, an Overview By Roozmehr Safi.
STATISTICS.
Cognitive Modelling – An exemplar-based context model Benjamin Moloney Student No:
Cognitive Modelling Assignment Suzanne Cotter March 2010.
Image Analysis Phases Image pre-processing –Noise suppression, linear and non-linear filters, deconvolution, etc. Image segmentation –Detection of objects.
4. FREQUENCY DISTRIBUTION
Conjunctive classification. What is conjunctive classification? In single-category classification, we want our model to give each test item to be classified.
Knowing Semantic memory.
Single Category Classification Stage One Additive Weighted Prototype Model.
Cognitive Modelling Assignment 1 MODEL 6: MSc Cognitive Science Elaine Cohalan Feb 9 th 2005.
Cognitive Modelling Experiment Clodagh Collins. Clodagh Collins.
Categorization vs. logic in category conjunction: towards a model of overextension Dr. Fintan Costello, Dept of Computer Science, University College Dublin.
1 Learning Entity Specific Models Stefan Niculescu Carnegie Mellon University November, 2003.
Tree Clustering & COBWEB. Remember: k-Means Clustering.
Assessing cognitive models What is the aim of cognitive modelling? To try and reproduce, using equations or similar, the mechanism that people are using.
Chapter 10 - Part 1 Factorial Experiments.
Exemplar-based accounts of “multiple system” phenomena in perceptual categorization R. M. Nosofsky and M. K. Johansen Presented by Chris Fagan.
Machine Learning: Ensemble Methods
CSCI 347 / CS 4206: Data Mining Module 04: Algorithms Topic 06: Regression.
Chapter 1: Introduction to Statistics
Chapter 1: Introduction to Statistics
1 Statistics This lecture covers chapter 1 and 2 sections in Howell Why study maths in psychology? “Mathematics has the advantage of teaching you.
Descriptive Statistics Used to describe the basic features of the data in any quantitative study. Both graphical displays and descriptive summary statistics.
Representing variables according to the ISO/IEC standard.
Disciplined Software Engineering Lecture #4 Software Engineering Institute Carnegie Mellon University Pittsburgh, PA Sponsored by the U.S. Department.
Naive Bayes Classifier
CountryData Technologies for Data Exchange SDMX Information Model: An Introduction.
Two Categories of Responders  Type 1 - Combinations of A and B treated as a fourth category (strategy evident in complete rejection of proposed categories.
Uses of Statistics: 1)Descriptive : To describe or summarize a collection of data points The data set in hand = the population of interest 2)Inferential.
Copyright © 1994 Carnegie Mellon University Disciplined Software Engineering - Lecture 1 1 Disciplined Software Engineering Lecture #4 Software Engineering.
Conjunctive classification. What is conjunctive classification? In single-category classification, we want our model to give each test item to be classified.
Thinking Mathematically
Chapter 11 Statistical Techniques. Data Warehouse and Data Mining Chapter 11 2 Chapter Objectives  Understand when linear regression is an appropriate.
Question paper 1997.
Slides for “Data Mining” by I. H. Witten and E. Frank.
Categories What are categories? The internal structure of categories Rule-based approaches Similarity-based approaches Theory-based approaches.
DATA MINING WITH CLUSTERING AND CLASSIFICATION Spring 2007, SJSU Benjamin Lam.
Adding a Sequence of numbers (Pairing Method)
Measures of Central Tendency
Number Sense Disambiguation Stuart Moore Supervised by: Anna Korhonen (Computer Lab)‏ Sabine Buchholz (Toshiba CRL)‏
IMPORTANCE OF STATISTICS MR.CHITHRAVEL.V ASST.PROFESSOR ACN.
Model Classification Model by Barry Hennessy. Model Basis My model was based on the Prototype model: that previously seen examples are combined into a.
Warm Up Solve each equation. 1. 2x – 5 = –17 2. –6 14
© 2012 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part.
Mathematical Formulas and Excel
CS Machine Learning Instance Based Learning (Adapted from various sources)
Combining Multiple Measures What are the indicators/ components? What are the priority outcomes? What are the performance expectations? How can we evaluate.
Lecture 8 – Categories 1 great detail is needed for planning & executing current responses some detail about context of new learning can be emcoded with.
Naïve Bayes Classifier April 25 th, Classification Methods (1) Manual classification Used by Yahoo!, Looksmart, about.com, ODP Very accurate when.
Review Design of experiments, histograms, average and standard deviation, normal approximation, measurement error, and probability.
Naive Bayes Classifier. REVIEW: Bayesian Methods Our focus this lecture: – Learning and classification methods based on probability theory. Bayes theorem.
Chapter 9 Knowledge. Some Questions to Consider Why is it difficult to decide if a particular object belongs to a particular category, such as “chair,”
Machine Learning: Ensemble Methods
Plan for Today’s Lecture(s)
Chapter 7. Classification and Prediction
Korean version of GloVe Applying GloVe & word2vec model to Korean corpus speaker : 양희정 date :
Matrices Rules & Operations.
Systems Analysis and Design in a Changing World, Fourth Edition
Naive Bayes Classifier
Statistics: The Z score and the normal distribution
Perceptrons Lirong Xia.
Measuring Social Life: How Many? How Much? What Type?
1 Chapter 1: Introduction to Statistics. 2 Variables A variable is a characteristic or condition that can change or take on different values. Most research.
Multi-Step Inequalities
Reasoning in Psychology Using Statistics
Reasoning in Psychology Using Statistics
Example 1A: Solving Multi-Step Inequalities
Perceptrons Lirong Xia.
Presentation transcript:

Single category classification What we have: Item to be classified, made up of attributes (dimensions) with values. Patient with a disease <eyes:cloudy, muscles:weak, skin:blotchy> Set of other items whose classification is known, also made up of attributes (dimensions) with values. Other patients with known diseases: <eyes:cloudy, muscles:weak, skin:pallid > Disease A <eyes:cloudy, muscles:twitchy, skin:blotchy > Disease A <eyes:dry, muscles:weak, skin:blotchy > Disease A <eyes:watery, muscles:weak, skin: pallid > Disease B <eyes: dry, muscles: taut, skin:damp > Disease B We want to compute new item’s degree of membership in category. (Sometimes it’s easier to view this attribute: value pairs abstractly, rather than in terms of concrete values.) <D1:A, D2:A D3:B > <D1:A, D2:B D3:A > <D1:B, D2:A D3:A > <D1:C, D2:A D3:B > <D1:B, D2:C D3:C >

Two theories Prototype theory. Each category has a prototype (a summary representation of its members). A new item to be classified is compared to all prototypes. The one to which it is most similar is the item’s membership category. Exemplar-based theory. When classifying an item in a category, we compare it to all previous members of all categories. The category to which the item has the highest summed membership is the item’s membership category. Computational modelling: How a prototype is formed? How similarity is computed? what parameters are used?

Additive weighted-attribute prototype model The prototype for a given category consists of a list, for each dimension available, of all possible values on that dimension. Values are weighted to show their relative importance for the category. The weight for any given value A on a dimension D for category C is W(<D:A>,C) = Number of occurrences of <D:A> in stored members of C Total number of occurrences of <D:A> across all categories The more often an attribute occurs in category C, the higher its weight will be in the prototype for that category and hence the more important it will be in that category. When classifying an item in a category, add the weights of that item’s attributes in that category’s prototype. The higher the total score, the better the item is as a member of that category.

Additive weighted prototype example Set of category items: < D1:A, D2:A, D3:B > Disease A < D1:A, D2:B, D3:A > Disease A < D1:B, D2:A, D3:A > Disease A < D1:C, D2:A, D3:B > Disease B < D1:B, D2:C, D3:C > Disease B Prototype for category A: D1 A2/2=1.0 B1/2=0.5 C0/1=0.0 D2 A2/3=0.67 B1/1=1.0 C0/1=0.0 D3 A2/2=1.0 B1/2= 0.5 C0/1 =0.0 Computing prototype weightings Classifying new items in A: Adding weights of new item’s attribute values <D1:C,D2:A,D3:B> = 0.0 + 0.67 + 0.5 = 1.17 <D1:A,D2:A,D3:B> = 1.0 + 0.67 + 0.5 = 2.17 <D1:A,D2:B,D3:A> = 1.0 + 1.0 + 1.0 = 3.0

An exemplar model: context theory When classifying an item in a category C, its degree of membership is equal to the sum of its similarity to all examples of that category, divided by its summed similarity to all examples of all categories. U is the set of all examples of all categories How is the similarity between two items (e.g. sim(x,i) ) computed? The exemplar model uses a multiplicative similarity computation: compare the item’s values on each dimension. If the values on a given dimension are the same, mark a 1 for that dimension. If the values on a given dimension are different, mark a parameter s (e.g. 0.2) for that dimension. Multiply the marked values for all dimensions to compute the overall similarity of the two items.

Context theory example Set of category items: < D1:A, D2:A, D3:B > Disease A < D1:A, D2:B, D3:A > Disease A < D1:B, D2:A, D3:A > Disease A < D1:C, D2:A, D3:B > Disease B < D1:B, D2:C, D3:C > Disease B We can pick whatever value we like for these parameters: we pick the ones that give the best fit to the data. Classifying new item <D1:C,D2:A,D3:B> in A: S3=0.5 S1=0.2 S2=0.3 <D1:C,D2:A,D3:B> <D1:A, D2:A, D3:B> = 0.2 * 1.0 * 1.0 = 0.20 < C, A, B> < A, B, A> = 0.2 * 0.5 * 0.3 = 0.03 < C, A, B> < B, A, A> = 0.2 * 1.0 * 0.3 = 0.06 < C, A, B> < C, A, B> = 1.0 * 1.0 * 1.0 = 1.00 < C, A, B> < B, C, C> = 0.2 * 0.5 * 1.0 = 0.10 0.20+0.03+0.06 0.20+0.03+0.06+1.00+0.10 Membership(<CAB>,A) = = 0.21

Your cognitive modelling work You will do cognitive modelling using either the additive-prototype model or the exemplar-based context models described here. You will model the results of an experiment on how people classified artificial items (described on three dimensions) in 3 previously-learned artificial categories. First you will model classification in single categories. Later you will model classification in conjunctions of those categories. The data to be used in your modelling work is available in an excel spreadsheet here http://inismor.ucd.ie/~fintanc/cogsci_masters/expt_spreadsheet.xls Try “introduction to excel” in Google if you haven’t used the excel spreadsheet before.

Overview of experiment Method: Investigates classification and overextension (logical errors) using a controlled set of patient-descriptions (items), symptoms (features on 3 dimensions) and categories (diseases A, B, and C). Training phase: 18 participants get a set of patient descriptions (training items) with certain diseases and symptoms, and learn to identify diseases (to criterion). Test phase: Participants get 5 new patient descriptions (test items) with new symptom combinations. For each test item participants separately rate patient as having disease A, B, C, A&B, A&C, B&C. Each test item therefore occurs 6 times in the test phase (with 6 different rating questions). Results. Classification scores and frequency of overextension errors.

Training items These disease categories have a family-resemblance structure: there are no simple rules linking an item’s symptoms and category membership. Participants learned categories by studying items like these. Different participants got different symptom-words in the training materials, but all had the same symptom distribution. Participants then classifed new “test” items in categories and category conjunctions. Item Symptoms Category EYES SKIN MUSCLES 1 Puffy Flaking Strained Disease A 2 Sunken Knotty 3 Pallid 4 Sweaty 5 Limp Diseases A&B 6 Blotchy Twitchy 7 Red Disease B 8 Cloudy 9 10 Jaundiced 11 12 Weak Disease C 13 14 15 16 17

Test items Symptoms rated as member of category or conjunction EYES SKIN MUSCLES A B C A&B A&C B&C 1 Puffy Jaundiced Weak ? 2 Sunken Flaking 3 Red Twitchy 4 Blotchy 5 Knotty Participants learned training items and then classified the test items as members or non-members of the categories and conjunctions. Your cognitive model will be given the training items and use the feature distribution there to compute the degree of membership for each test item in each category, and later in each conjunction. This degree of membership will be compared with the observed average degree of membership in the experiment.