Detecting and Correcting Errors of Omission After Explanation-based Learning
|
|
- Gladys Goodwin
- 8 years ago
- Views:
Transcription
1 Detecting and Correcting Errors of Omission After Explanation-based Learning Michael J. Pazzani Department of Information and Computer Science University of California, Irvine, CA IJCAI-89 Monday, August 14, 1989
2 Outline I. Problem: A. Detecting errors in generalization produced by EBL B. Assigning blame to rules in domain theory C. Correcting domain theory II. Types of Errors A. Errors of Omission- Fail to make correct prediction B. Errors of Commission - Make incorrect prediction III. Indexing generalizations in Memory A. Explanatory- Given result, Predict cause B. Predictive- Given action, Predict result IV. Unsupervised detection of errors of omission V. Blame Assignment & revising domain theory VI. Experimental Results 2 IJCAI-89 Monday, August 14, 1989
3 Background: OCCAM Performance task Predict outcome of economic sanction incidents Outcome inferred by hierarchical classification Error of omission occurs if incident cannot be classified Error of commission occurs if incident is classified incorrectly coerce s1 s2 s3 s5 s6 s7 s8 Learning Method: Combines empirical and explanation-based learning empirical techniques learn the domain theory used by EBL Problem: incorrect domain theory incorrect generalizations 3 IJCAI-89 Monday, August 14, 1989
4 Types of examples: Terminology Foundational: examples from which the domain theory is learned E.g., Parent helping child Performance: examples of the performance task E.g., Kidnapping examples Foundational examples are subproblems of the performance task. Performance examples are examples of the performance task. Distinction is relative to task. If task is predicting whom to sell ransom insurance to, the kidnapping examples are foundational. Types of rules (or schemata) Domain: used by EBL to explain performance example Compiled: created by EBL to be used in performance task. 4 IJCAI-89 Monday, August 14, 1989
5 Problem Statement: Rule in domain theory are learned (or hand-coded) Parents have a goal of preserving their children s health Create compiled rule with EBL One plan to obtain money is to threaten to kill the child of a rich person. Detect error of omission in compiled rule from performance example A kidnapper obtains money from grandparent of hostage. Assign Blame for error on rule in domain theory Revise rule in domain theory Members of the same family have a goal of preserving each other s health Revise Rule in compiled theory 5 IJCAI-89 Monday, August 14, 1989
6 Why Errors of Omission? Only type of error created by one-sided learning algorithms Incremental, hill-climbing algorithms (Langley et al., 1987). Accounts for some human learning Grammar: (Berwick, 1986) Concept Acquisition (Bruner, et al, 1956) Subject of theoretical analysis (Valiant, 84; Haussler, 87) Hypothesis never more general than true hypothesis. Incremental blame assignment and revision possible: Error of Omission: One of the domain theory rules used to create a compiled rule needs to be generalized by dropping a condition that is not present in a performance example Error of commission: One of the domain theory rules used to create a compiled rule needs to be specialized by adding a condition that is present in a new performance example. 6 IJCAI-89 Monday, August 14, 1989
7 Unsupervised detection of error of omission coerce s1 s2 s3 s5 s6 s7 s8 Problem: Find a schema in memory that would predict the outcome of a new performance example, if the schema were more general. Approach: Distinguish between two uses of schemata Predictive: What would happen if the United States refused to sell computers to South Korea unless South Korea stopped exporting automobiles to Canada? Explanatory: What could cause the price of oil to rise? 7 IJCAI-89 Monday, August 14, 1989
8 Derivation and use of Indices Derived analytically: explanatory: Features from consequent of domain rules. predictive: Features from antecedent of domain rules. Use during retrieval: explanatory: Finding a schema to explain the cause of an outcome predictive: Finding a schema to predict the outcome of an event. Determining indices: An example Australia and France, 1983 In 1983, Australia refused to sell uranium to France, unless France ceased nuclear testing in the South Pacific. France paid a higher price to buy uranium from South Africa and continued nuclear testing. Processing goal: Explain result (France buys uranium elsewhere) 8 IJCAI-89 Monday, August 14, 1989
9 Determining indices: An example 1. Threat -> Increased demand (ACT TYPE (SELL) ACTOR (POLITY EXPORTS?Y ECONOMY (FREE)) TO?X:(POLITY IMPORTS?Y ECONOMY (FREE)) OBJECT?Y:(COMMODITY) MODE (NEG)) 2. Increased demand -> Willingness to pay higher price 3. Purchase -> Possess result (STATE TYPE (DEMAND-INCREASE) ACTOR?X OBJECT?Y) 9 IJCAI-89 Monday, August 14, 1989
10 Indexing by predictive and explanatory features A B C D coerce actor target... response outcome (coerce actor (polity exports =OBJECT economy (free)) target (polity economic-health (strong) economy (free) imports =OBJECT)... response (act type (sell) actor (polity bus-rel =TARGET exports =OBJECT) object =OBJECT price (money value (>market)) to =TARGET) outcome (goal-outcome type (failure)) 10 IJCAI-89 Monday, August 14, 1989
11 Detecting an error of omission input: New performance example Hierarchy of schema (domain & compiled theory) Retrieve schema by following predictive indices If schema has outcome, Then If outcome of example and schema agree Then EXIT Else Error of commission Else If example is explainable Then EBL(example) Else If retrieve schema by explanatory indices Then attempt blame assignment Else TDL(example) or SBL(example) Find a schema sufficiently close to the performance example that would explain the example if generalized. 11 IJCAI-89 Monday, August 14, 1989
12 Blame assignment (defining sufficiently close ) 1. Reexplain the schema with EBL that maintains dependencies between constraints in the compiled rule and rules in the domain theory. (Trade-off between storing & recomputing): (coerce target (polity economic-health (strong) <- Rule.013 economy (free) <- Rule.012 imports =OBJECT) <- {Rule.01 Rule.13} 2. Find differences between the schema and the new event. 3. Collect inference rules responsible for differences. 4. If one inference rule is responsible for all the differences, then assign blame to this inference rule. 12 IJCAI-89 Monday, August 14, 1989
13 Blame assignment: An example US and USSR, 1980 In 1980, the US refused to sell grain to the Soviet Union if the Soviet Union did not withdraw its troops from Afghanistan. The Soviet Union paid a higher price to buy grain from Argentina and did not withdraw from Afghanistan. 2. Find differences: (coerce target (polity economy (free))) 3. Collect rules: {rule.12} 13 IJCAI-89 Monday, August 14, 1989
14 Correcting the domain theory Convert performance example to foundational example: (COERCE ACTOR (POLITY NAME (US) ECONOMY (FREE)...) TARGET (POLITY NAME (USSR) ECONOMY (CONTROLLED)...) THREAT (ACT TYPE (SELL) ACTOR =ACTOR TO =TARGET MODE (NEG)) (ACT TYPE (SELL) ACTOR (POLITY TYPE (COUNTRY) NAME (US) ECONOMY (FREE)...) TO (POLITY TYPE (COUNTRY) NAME (USSR) ECONOMY (CONTROLLED)...) OBJECT (COMMODITY AVAILABILITY (COMMON) TYPE (GRAIN)) MODE (NEG)) RESULT (STATE TYPE (DEMAND-INCREASE) ACTOR (POLITY NAME (USSR)...) OBJECT (COMMODITY TYPE (GRAIN)...) 14 IJCAI-89 Monday, August 14, 1989
15 Correcting the domain theory (cont d) Generalize antecedent of rule to accommodate new example: Old: (ACT TYPE (SELL) ACTOR (POLITY EXPORTS?Y ECONOMY (FREE)) TO?X:(POLITY IMPORTS?Y ECONOMY (FREE)) OBJECT?Y:(COMMODITY) MODE (NEG)) New: (ACT TYPE (SELL) ACTOR (POLITY EXPORTS?Y ECONOMY (FREE)) TO?X:(POLITY IMPORTS?Y) OBJECT?Y:(COMMODITY) MODE (NEG)) Maximally specific conjunctive generalization assumes no noise. 15 IJCAI-89 Monday, August 14, 1989
16 Experimental Design 1.0 All rules that indicate effect of threat were modified by conjoining all preconditions. (cf. Kolodner, 1984) Run on economic sanction database (15, actual, 5 hypo) Accuracy measured after 10 and 15 examples for 10 trials. Accuracy Number of examples occam occam+errors occam+errors+ correction Results OCCAM with error correction more accurate than OCCAM p<.005, t(18)=3.16 OCCAM with correct knowledge base more accurate (few examples) 16 IJCAI-89 Monday, August 14, 1989
17 Related Work Recovering from incorrect knowledge in SOAR (Laird, 1988) patches compiled theory to avoid incorrect knowledge doesn t update domain theory may require patching for each use ML-SMART (Bergadano et al., 1988) Batch system that works on complete set of examples can handle errors of commission supervised Theory Revision (Ginsberg, 1988) Batch system Can handle classification noise supervised can handle errors of commission 17 IJCAI-89 Monday, August 14, 1989
18 Conclusion I. Unsupervised detection of errors of omission requires distinguishing between explanatory and predictive uses of schemata. II. Assigning blame on rules in the domain theory for errors in compiled theory can be accomplished by maintaining dependencies between conditions of compiled rule and a rule in the domain theory 18 IJCAI-89 Monday, August 14, 1989
Detecting and Correcting Errors of Omission After Explanation-based Learning
Detecting and Correcting Errors of Omission After Explanation-based Learning Michael J. Pazzani Department of Information and Computer Science University of California, Irvine, CA 92717 pazzani@ics.uci.edu
More informationRepresentation of Electronic Mail Filtering Profiles: A User Study
Representation of Electronic Mail Filtering Profiles: A User Study Michael J. Pazzani Department of Information and Computer Science University of California, Irvine Irvine, CA 92697 +1 949 824 5888 pazzani@ics.uci.edu
More informationEconomics 380: International Economics Fall 2000 Exam #2 100 Points
Economics 380: International Economics Fall 2000 Exam #2 100 Points Name (ID) YOU SHOULD HAVE 7 PAGES FOR THIS EXAM. EXAM WILL END AT 1:50. MAKE SURE YOUR NAME IS ON THE FIRST AND LAST PAGE OF THE EXAM.
More informationGuidelines of China Financial Futures Exchange on Monitoring Abnormal Transactions Monitoring Abnormal Transactions (Trial)
Guidelines of China Financial Futures Exchange on Monitoring Abnormal Transactions Monitoring Abnormal Transactions (Trial) (Adopted on November 15, 2010; amended for the first time on April 10, 2015)
More informationChapter 10. Practical Database Design Methodology. The Role of Information Systems in Organizations. Practical Database Design Methodology
Chapter 10 Practical Database Design Methodology Practical Database Design Methodology Design methodology Target database managed by some type of database management system Various design methodologies
More informationSDMX technical standards Data validation and other major enhancements
SDMX technical standards Data validation and other major enhancements Vincenzo Del Vecchio - Bank of Italy 1 Statistical Data and Metadata exchange Original scope: the exchange Statistical Institutions
More informationMGE#12 The Balance of Payments
MGE#12 The Balance of Payments The Current Account, the Capital Account and the Balance of Payments Introduction to the Foreign Exchange Market Savings, Investment and the Current Account 1 From last session
More informationPrediction of Stock Performance Using Analytical Techniques
136 JOURNAL OF EMERGING TECHNOLOGIES IN WEB INTELLIGENCE, VOL. 5, NO. 2, MAY 2013 Prediction of Stock Performance Using Analytical Techniques Carol Hargreaves Institute of Systems Science National University
More informationClustering Connectionist and Statistical Language Processing
Clustering Connectionist and Statistical Language Processing Frank Keller keller@coli.uni-sb.de Computerlinguistik Universität des Saarlandes Clustering p.1/21 Overview clustering vs. classification supervised
More informationData, Measurements, Features
Data, Measurements, Features Middle East Technical University Dep. of Computer Engineering 2009 compiled by V. Atalay What do you think of when someone says Data? We might abstract the idea that data are
More informationIntroduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski trajkovski@nyus.edu.mk
Introduction to Machine Learning and Data Mining Prof. Dr. Igor Trajkovski trajkovski@nyus.edu.mk Ensembles 2 Learning Ensembles Learn multiple alternative definitions of a concept using different training
More informationNotes for Lecture 2 (February 7)
CONTINUOUS COMPOUNDING Invest $1 for one year at interest rate r. Annual compounding: you get $(1+r). Semi-annual compounding: you get $(1 + (r/2)) 2. Continuous compounding: you get $e r. Invest $1 for
More informationThe Mortgage Brokerages and Mortgage Administrators Act
MORTGAGE BROKERAGES AND 1 The Mortgage Brokerages and Mortgage Administrators Act being Chapter M-20.1* of The Statutes of Saskatchewan, 2007 (effective October 1, 2010), as amended by the Statutes of
More informationCapital Structure: Informational and Agency Considerations
Capital Structure: Informational and Agency Considerations The Big Picture: Part I - Financing A. Identifying Funding Needs Feb 6 Feb 11 Case: Wilson Lumber 1 Case: Wilson Lumber 2 B. Optimal Capital Structure:
More informationBorgatti, Steven, Everett, Martin, Johnson, Jeffrey (2013) Analyzing Social Networks Sage
Social Network Analysis in Cultural Anthropology Instructor: Dr. Jeffrey C. Johnson and Dr. Christopher McCarty Email: johnsonje@ecu.edu and ufchris@ufl.edu Description and Objectives Social network analysis
More informationA Study Of Bagging And Boosting Approaches To Develop Meta-Classifier
A Study Of Bagging And Boosting Approaches To Develop Meta-Classifier G.T. Prasanna Kumari Associate Professor, Dept of Computer Science and Engineering, Gokula Krishna College of Engg, Sullurpet-524121,
More informationImage Lab Software for the GS-900 Densitometer
Image Lab Software for the GS-900 Densitometer Quick Start Guide Catalog # 170-9690 Bio-Rad Technical Support For help and technical advice, please contact the Bio-Rad Technical Support department. In
More informationAnalytical Data Sourcing and Optimization
Analytical Data Sourcing and Optimization Willy Sennott Sr. Director, Business Analytics & Research, People to People Ambassador Programs Ozgur Dogan SVP, Data Solutions Leader, Merkle Presenter Backgrounds
More informationClassifying Large Data Sets Using SVMs with Hierarchical Clusters. Presented by :Limou Wang
Classifying Large Data Sets Using SVMs with Hierarchical Clusters Presented by :Limou Wang Overview SVM Overview Motivation Hierarchical micro-clustering algorithm Clustering-Based SVM (CB-SVM) Experimental
More informationIntroduction to Learning & Decision Trees
Artificial Intelligence: Representation and Problem Solving 5-38 April 0, 2007 Introduction to Learning & Decision Trees Learning and Decision Trees to learning What is learning? - more than just memorizing
More informationAutomatic Document Categorization A Hummingbird White Paper
Automatic Document Categorization A Hummingbird White Paper Automatic Document Categorization While every attempt has been made to ensure the accuracy and completeness of the information in this document,
More informationComparison of K-means and Backpropagation Data Mining Algorithms
Comparison of K-means and Backpropagation Data Mining Algorithms Nitu Mathuriya, Dr. Ashish Bansal Abstract Data mining has got more and more mature as a field of basic research in computer science and
More informationUnsupervised Data Mining (Clustering)
Unsupervised Data Mining (Clustering) Javier Béjar KEMLG December 01 Javier Béjar (KEMLG) Unsupervised Data Mining (Clustering) December 01 1 / 51 Introduction Clustering in KDD One of the main tasks in
More informationFacebook Friend Suggestion Eytan Daniyalzade and Tim Lipus
Facebook Friend Suggestion Eytan Daniyalzade and Tim Lipus 1. Introduction Facebook is a social networking website with an open platform that enables developers to extract and utilize user information
More informationUsing LSI for Implementing Document Management Systems Turning unstructured data from a liability to an asset.
White Paper Using LSI for Implementing Document Management Systems Turning unstructured data from a liability to an asset. Using LSI for Implementing Document Management Systems By Mike Harrison, Director,
More informationCopyright 2007 Ramez Elmasri and Shamkant B. Navathe. Slide 29-1
Slide 29-1 Chapter 29 Overview of Data Warehousing and OLAP Chapter 29 Outline Purpose of Data Warehousing Introduction, Definitions, and Terminology Comparison with Traditional Databases Characteristics
More informationThe primary goal of this thesis was to understand how the spatial dependence of
5 General discussion 5.1 Introduction The primary goal of this thesis was to understand how the spatial dependence of consumer attitudes can be modeled, what additional benefits the recovering of spatial
More informationCS 2750 Machine Learning. Lecture 1. Machine Learning. http://www.cs.pitt.edu/~milos/courses/cs2750/ CS 2750 Machine Learning.
Lecture Machine Learning Milos Hauskrecht milos@cs.pitt.edu 539 Sennott Square, x5 http://www.cs.pitt.edu/~milos/courses/cs75/ Administration Instructor: Milos Hauskrecht milos@cs.pitt.edu 539 Sennott
More informationSocial Perception and Attribution
4 Social Perception and Attribution Chapter An Information Processing Model of Perception Stereotypes: Perceptions about Groups of People Self-Fulfilling Prophecy: The Pygmalion Effect Causal Attribution
More informationCollective Behavior Prediction in Social Media. Lei Tang Data Mining & Machine Learning Group Arizona State University
Collective Behavior Prediction in Social Media Lei Tang Data Mining & Machine Learning Group Arizona State University Social Media Landscape Social Network Content Sharing Social Media Blogs Wiki Forum
More informationTo this end ERCI fully endorses and adheres to the Principles of Personal Data Protection Act (2012). 1. The Purpose:
Data Protection Policy: Policy Statement: ERC Institute (ERCI) collects and uses information about people with whom it communicates. As stipulated by the Personal Data Protection Act (2012) (hereinafter
More informationPage 1/.. USA / Canada - South Africa Schedule No. 4 / 2011-Jan-24
USA / Canada South Africa Schedule No. 4 / 2011Jan24 Page 1/.. USA / Canada South Africa Schedule No. 4 / 2011Jan24 Page 2/.. USA / Canada South Africa Schedule No. 4 / 2011Jan24 Page 3/.. USA / Canada
More informationTeamstudio USER GUIDE
Teamstudio Software Engineering Tools for IBM Lotus Notes and Domino USER GUIDE Edition 30 Copyright Notice This User Guide documents the entire Teamstudio product suite, including: Teamstudio Analyzer
More informationDE 7090 DISTANCE EDUCATION. M.Com. (Marketing) DEGREE EXAMINATION, DECEMBER 2013. MANAGEMENT CONCEPTS. SECTION A (5 8 = 40 marks)
Ws 5 DE 7090 11 DISTANCE EDUCATION M.Com. (Marketing) DEGREE EXAMINATION, DECEMBER 2013. MANAGEMENT CONCEPTS Time : Three hours Maximum : 100 marks SECTION A (5 8 = 40 marks) Answer any FIVE questions.
More informationlarge-scale machine learning revisited Léon Bottou Microsoft Research (NYC)
large-scale machine learning revisited Léon Bottou Microsoft Research (NYC) 1 three frequent ideas in machine learning. independent and identically distributed data This experimental paradigm has driven
More informationMultiagent Reputation Management to Achieve Robust Software Using Redundancy
Multiagent Reputation Management to Achieve Robust Software Using Redundancy Rajesh Turlapati and Michael N. Huhns Center for Information Technology, University of South Carolina Columbia, SC 29208 {turlapat,huhns}@engr.sc.edu
More informationInternational Business Plan A PRACTICAL GUIDE FOR EXPORTERS
International Business Plan A PRACTICAL GUIDE FOR EXPORTERS ÍNDICE 1 TABLE OF CONTENTS PLAN STRUCTURE 5 SECTIONS 6 EXPLANATORY NOTES 36 CASE STUDY 67 This is a sampble of 18 pages out of 97 of the International
More informationChapter 10 Practical Database Design Methodology and Use of UML Diagrams
Chapter 10 Practical Database Design Methodology and Use of UML Diagrams Copyright 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 10 Outline The Role of Information Systems in
More informationNORTH DAKOTA PERSONAL INJURY PROTECTION ENDORSEMENT
COMMERCIAL AUTO CA 22 34 10 13 THIS ENDORSEMENT CHANGES THE POLICY. PLEASE READ IT CAREFULLY. NORTH DAKOTA PERSONAL INJURY PROTECTION ENDORSEMENT For a covered "auto" licensed or principally garaged in,
More informationWeb-Scale Extraction of Structured Data Michael J. Cafarella, Jayant Madhavan & Alon Halevy
The Deep Web: Surfacing Hidden Value Michael K. Bergman Web-Scale Extraction of Structured Data Michael J. Cafarella, Jayant Madhavan & Alon Halevy Presented by Mat Kelly CS895 Web-based Information Retrieval
More informationCorrelational Research
Correlational Research Chapter Fifteen Correlational Research Chapter Fifteen Bring folder of readings The Nature of Correlational Research Correlational Research is also known as Associational Research.
More informationLehrstuhl für Informatik 2
Analytical Learning Introduction Lehrstuhl Explanation is used to distinguish the relevant features of the training examples from the irrelevant ones, so that the examples can be generalised Introduction
More informationUNCLASSIFIED. Briefing to Critical Infrastructure Sector Organizations on the Canadian Cyber Incident Response Centre (CCIRC)
Briefing to Critical Infrastructure Sector Organizations on the Canadian Cyber Incident Response Centre (CCIRC) Cyber in the News 1 Tactics, Techniques and Procedures These observed tactics, techniques
More informationIntroduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski trajkovski@nyus.edu.mk
Introduction to Machine Learning and Data Mining Prof. Dr. Igor Trakovski trakovski@nyus.edu.mk Neural Networks 2 Neural Networks Analogy to biological neural systems, the most robust learning systems
More informationFAQ v1.01. Note: ICHI is not a Synergy FX product. How to run the Ichi FX EA Robot? What currency does Ichi run on? Please refer to the videos below:
FAQ v1.01 Note: ICHI is not a Synergy FX product How to run the Ichi FX EA Robot? Please refer to the videos below: The video for running Ichi is on Vimeo the link is: http://vimeo.com/ichifx/runningichiea
More informationIntegration of an open source rule engine to enhance the IHTSDO Workbench testing
Integration of an open source rule engine to enhance the IHTSDO Workbench testing Dr. Guillermo Reynoso Dr. Alejandro Lopez Osornio termmed IT Buenos Aires, Argentina 2009 termmed SA Terminology maintenance
More informationCourse 395: Machine Learning
Course 395: Machine Learning Lecturers: Maja Pantic (maja@doc.ic.ac.uk) Stavros Petridis (sp104@doc.ic.ac.uk) Goal (Lectures): To present basic theoretical concepts and key algorithms that form the core
More informationMachine Learning Capacity and Performance Analysis and R
Machine Learning and R May 3, 11 30 25 15 10 5 25 15 10 5 30 25 15 10 5 0 2 4 6 8 101214161822 0 2 4 6 8 101214161822 0 2 4 6 8 101214161822 100 80 60 40 100 80 60 40 100 80 60 40 30 25 15 10 5 25 15 10
More informationPosition Classification Flysheet for Logistics Management Series, GS-0346
Position Classification Flysheet for Logistics Management Series, GS-0346 Table of Contents SERIES DEFINITION... 2 SERIES COVERAGE... 2 EXCLUSIONS... 4 DISTINGUISHING BETWEEN LOGISTICS MANAGEMENT AND OTHER
More informationSTATE OF THE DATA CENTER SURVEY GERMANY RESULTS
STATE OF THE DATA CENTER SURVEY GERMANY RESULTS SEPTEMBER 2012 CONTENTS 3 METHODOLOGY 4 INTRODUCTION 5 DATA CENTER COMPLEXITY IS PERVASIVE 6 EFFECTS OF DATA CENTER COMPLEXITY ARE DIVERSE AND COSTLY 8 IT
More informationDo you know? "7 Practices" for a Reliable Requirements Management. by Software Process Engineering Inc. translated by Sparx Systems Japan Co., Ltd.
Do you know? "7 Practices" for a Reliable Requirements Management by Software Process Engineering Inc. translated by Sparx Systems Japan Co., Ltd. In this white paper, we focus on the "Requirements Management,"
More informationLearning Objectives. Strategic Planning Concepts for Marketing Communications. Strategic Planning. Business Planning Process.
CHAPTER 4 Strategic Planning Concepts for Marketing Communications Learning Objectives Identify the distinctions and relationships between the various types of planning Describe the key variables that
More informationGeneral Information Series
General Information Series 1 Agricultural Futures for the Beginner Describes various applications of futures contracts for those new to futures markets. Different trading examples for hedgers and speculators
More informationCREDIT REPORTING PRIVACY CODE (CR Code) Draft v.3.1
CREDIT REPORTING PRIVACY CODE () Draft v.3.1 This is intended to replace the Credit Reporting Code of Conduct issued under Section 18A of the Privacy Act 1988 (this section is repealed with effect from
More informationENDOWMENT & FOUNDATION GOVERNANCE: FIDUCIARY OVERSIGHT AND IMPLEMENTATION MAY 2013
ENDOWMENT & FOUNDATION GOVERNANCE: FIDUCIARY OVERSIGHT AND IMPLEMENTATION MAY 2013 WHAT IS FIDUCIARY GOVERNANCE AND WHY IS IT IMPORTANT? Fulfillment of fiduciary responsibilities requires more than understanding
More informationMultiple Kernel Learning on the Limit Order Book
JMLR: Workshop and Conference Proceedings 11 (2010) 167 174 Workshop on Applications of Pattern Analysis Multiple Kernel Learning on the Limit Order Book Tristan Fletcher Zakria Hussain John Shawe-Taylor
More informationPerspectives on Data Mining
Perspectives on Data Mining Niall Adams Department of Mathematics, Imperial College London n.adams@imperial.ac.uk April 2009 Objectives Give an introductory overview of data mining (DM) (or Knowledge Discovery
More informationCLINICAL PSYCHOLOGY PSYC 450-001 (3 credit hours) Fall 2015
CLINICAL PSYCHOLOGY PSYC 450-001 (3 credit hours) Fall 2015 Instructor: Dr. Jason Murphy Office: Alumni Hall 0123 Office Hours: Mondays, 2:00-3:00 p.m., 4:15-6:00 p.m.; Wednesdays, 1:00-3:00 p.m. Office
More informationA Security Specification Language (SSL) for Run-Time Policy Enforcement
A Security Specification Language (SSL) for Run-Time Policy Enforcement Topic Area: Design approaches and Run Time Assurance for Highly Dynamic Systems Sandeep Shukla FERMAT Lab, Centre for Embedded Systems
More informationHow does a venture capitalist appraise investment opportunities?
1 How does a venture capitalist appraise investment opportunities? Michael Queen - Finance Director, 3i Group plc A presentation to: 23 Pensions Convention 2 June 23 A How presentation does a venture to:
More informationInformation Security Skills: A Comparison Of What Is Used And What Is Taught
1 Information Security Skills: A Comparison Of What Is Used And What Is Taught Albert L. Fundaburk SH 239 Bloomsburg University Bloomsburg, PA 17815 Ph. (570) 389-9621 Fax (570) 389-3892 Email afundabr@bloomu.edu
More informationOntario Automobile Policy (OAP 1)
Ontario Automobile Policy (OAP 1) Owner's Policy Approved by the Superintendent of Financial Services for use as the standard Owner's Policy on or after January 1, 2001. About This Policy This is your
More informationEarly release of superannuation Information on accessing your superannuation before retirement age
Early release of superannuation Information on accessing your superannuation before retirement age www.apra.gov.au Australian Prudential Regulation Authority What this brochure is about In Australia, superannuation
More informationOracle Sales Compensation
Oracle Sales Compensation Implementation Guide Release 11i August 2000 Part No. A86178-01 Oracle Sales Compensation Implementation Guide, Release 11i Part No. A86178-01 Copyright 2000, Oracle Corporation.
More informationSHARE TRADING POLICY. This securities trading policy (Trading Policy) is a policy of Strategic Elements Limited and of all its subsidiaries (Company).
Strategic Elements Ltd ABN 47 122 437 503 Suite 6/27 Railway Road Subiaco WA 6008 Australia Phone: +61 8 9278 2788 Fax: +61 8 9288 4400 admin@strategicelements.com.a u SHARE TRADING POLICY 1. INTRODUCTION
More informationJune 2015 FLSA: EXEMPT ASSOCIATE DEAN, CAREER EDUCATION AND WORKFORCE DEVELOPMENT
June 2015 FLSA: EXEMPT ASSOCIATE DEAN, CAREER EDUCATION AND WORKFORCE DEVELOPMENT DEFINITION Under administrative direction of the Dean, School of Continuing Education, the Associate Dean, Career Education
More informationAGREEMENT ON AN INTERNATIONAL ENERGY PROGRAM. (As amended 30 November 2007)
AGREEMENT ON AN INTERNATIONAL ENERGY PROGRAM (As amended 0 November 2007) AGREEMENT ON AN INTERNATIONAL ENERGY PROGRAM (As amended 0 November 2007) TABLE OF CONTENTS PREAMBLE Article 1... 6 Chapter I EMERGENCY
More informationWeb Data Extraction: 1 o Semestre 2007/2008
Web Data : Given Slides baseados nos slides oficiais do livro Web Data Mining c Bing Liu, Springer, December, 2006. Departamento de Engenharia Informática Instituto Superior Técnico 1 o Semestre 2007/2008
More informationAccounting Benchmark statements
Accounting Benchmark statements Academic standards - Accounting 1. Defining principles 1.1. This statement is intended to cover programmes of study in accounting at institutions of higher education in
More informationTHIS POSITION IS ONLY OPEN TO CLASSIFIED EMPLOYEES (NON-PROBATIONARY) IN THE FOPE UNTIL NOVEMBER 20, 2015
Human Resources Department 121 S.W. Port St. Lucie Blvd Port St. Lucie, FL 34984-5099 www.cityofpsl.com THIS POSITION IS ONLY OPEN TO CLASSIFIED EMPLOYEES (NON-PROBATIONARY) IN THE FOPE UNTIL NOVEMBER
More informationOCCUPATIONAL STANDARD (For use in the development of supply chain related job descriptions, performance evaluations, career development plans, etc.
OCCUPATIONAL STANDARD (For use in the development of supply chain related job descriptions, performance evaluations, career development plans, etc.) Description of Position (As defined by the CSCSC Stakeholder
More informationChapter ML:XI (continued)
Chapter ML:XI (continued) XI. Cluster Analysis Data Mining Overview Cluster Analysis Basics Hierarchical Cluster Analysis Iterative Cluster Analysis Density-Based Cluster Analysis Cluster Evaluation Constrained
More informationData Mining - Evaluation of Classifiers
Data Mining - Evaluation of Classifiers Lecturer: JERZY STEFANOWSKI Institute of Computing Sciences Poznan University of Technology Poznan, Poland Lecture 4 SE Master Course 2008/2009 revised for 2010
More informationNeutralus Certification Practices Statement
Neutralus Certification Practices Statement Version 2.8 April, 2013 INDEX INDEX...1 1.0 INTRODUCTION...3 1.1 Overview...3 1.2 Policy Identification...3 1.3 Community & Applicability...3 1.4 Contact Details...3
More informationBUSINESS ON-LINE BANKING AGREEMENT
BUSINESS ON-LINE BANKING AGREEMENT THIS BUSINESS ON-LINE BANKING AGREEMENT (this Agreement ) is for Business On-Line Banking Services provided by First National Bank of Northern California, ( Bank or we
More informationInsider Trading Policy
Insider Trading Policy Yancoal Australia Limited ACN 111 859 119 Approved 26 June 2012 Policy 1 Objective The purpose of this Policy is to incorporate into Yancoal s policies a prohibition of the types
More informationGPSQL Miner: SQL-Grammar Genetic Programming in Data Mining
GPSQL Miner: SQL-Grammar Genetic Programming in Data Mining Celso Y. Ishida, Aurora T. R. Pozo Computer Science Department - Federal University of Paraná PO Box: 19081, Centro Politécnico - Jardim das
More informationCFSD 21 ST CENTURY SKILL RUBRIC CRITICAL & CREATIVE THINKING
Critical and creative thinking (higher order thinking) refer to a set of cognitive skills or strategies that increases the probability of a desired outcome. In an information- rich society, the quality
More informationOracle9i Data Warehouse Review. Robert F. Edwards Dulcian, Inc.
Oracle9i Data Warehouse Review Robert F. Edwards Dulcian, Inc. Agenda Oracle9i Server OLAP Server Analytical SQL Data Mining ETL Warehouse Builder 3i Oracle 9i Server Overview 9i Server = Data Warehouse
More informationAsset Suite Improve your performance, safety and analysis
Asset Suite Improve your performance, safety and analysis Asset Suite is a complete solution that helps you effectively manage assets and MRO costs to achieve the high level of performance, safety and
More informationONTOLOGY-BASED GENERIC TEMPLATE FOR RETAIL ANALYTICS
ONTOLOGY-BASED GENERIC TEMPLATE FOR RETAIL ANALYTICS Kenneth I. Davou 1 and Rosnah Idrus 2 1 Universiti Sains Malaysia (USM), Malaysia, kid11_ttm071@student.usm.my 2 Universiti Sains Malaysia (USM), Malaysia,
More informationCross-Certification and PKI Policy Networking
Entrust Cross-Certification and PKI Policy Networking Author: Jim Turnbull Date: August 2000 Version: 1.0 Copyright 2000-2003 Entrust. All rights reserved. 1 Entrust is a registered trademark of Entrust,
More informationSUPPORTING LOGISTICS DECISIONS BY USING COST AND PERFORMANCE MANAGEMENT TOOLS. Zoltán BOKOR. Abstract. 1. Introduction
SUPPORTING LOGISTICS DECISIONS BY USING COST AND PERFORMANCE MANAGEMENT TOOLS Zoltán BOKOR Department of Transport Economics Faculty of Transportation Engineering Budapest University of Technology and
More informationProblems and Measures Regarding Waste 1 Management and 3R Era of public health improvement Situation subsequent to the Meiji Restoration
More information
TimeValue Software Due Date Tracking and Task Management Software
User s Guide TM TimeValue Software Due Date Tracking and Task Management Software File In Time Software User s Guide Copyright TimeValue Software, Inc. (a California Corporation) 1992-2010. All rights
More information15 Organisation/ICT/02/01/15 Back- up
15 Organisation/ICT/02/01/15 Back- up 15.1 Description Backup is a copy of a program or file that is stored separately from the original. These duplicated copies of data on different storage media or additional
More informationReport on the Dagstuhl Seminar Data Quality on the Web
Report on the Dagstuhl Seminar Data Quality on the Web Michael Gertz M. Tamer Özsu Gunter Saake Kai-Uwe Sattler U of California at Davis, U.S.A. U of Waterloo, Canada U of Magdeburg, Germany TU Ilmenau,
More informationPART I DEPARTMENT OF PERSONNEL SERIVCES 4.140 STATE OF HAWAII 4.142... 4.144 MEDICAL RECORD TECHNICIAN SERIES
PART I DEPARTMENT OF PERSONNEL SERIVCES 4.140 STATE OF HAWAII 4.142................................................................ 4.144 Class Specifications for the: MEDICAL RECORD TECHNICIAN SERIES
More informationInfiniteInsight 6.5 sp4
End User Documentation Document Version: 1.0 2013-11-19 CUSTOMER InfiniteInsight 6.5 sp4 Toolkit User Guide Table of Contents Table of Contents About this Document 3 Common Steps 4 Selecting a Data Set...
More informationChapter 8 The Enhanced Entity- Relationship (EER) Model
Chapter 8 The Enhanced Entity- Relationship (EER) Model Copyright 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 8 Outline Subclasses, Superclasses, and Inheritance Specialization
More informationNatural Gas and Greenhouse Gases. OLLI Lectures November 2014 Dennis Silverman Physics and Astronomy UC Irvine
Natural Gas and Greenhouse Gases OLLI Lectures November 2014 Dennis Silverman Physics and Astronomy UC Irvine Replacing Coal With Natural Gas Greenhouse Gas Reduction by Switching from Coal to Natural
More informationOPRE504 Chapter Study Guide Chapter 7 Randomness and Probability. Terminology of Probability. Probability Rules:
OPRE504 Chapter Study Guide Chapter 7 Randomness and Probability Terminology of Probability For a Random phenomenon, there are a number of possible Outcomes. For example, tossing a coin could result in
More informationFRAMEWORK FOR THE PREPARATION OF ACCOUNTS. Best Practice Guidance
FRAMEWORK FOR THE PREPARATION OF ACCOUNTS Best Practice Guidance Revised Edition April 2010 PUBLISHED IN APRIL 2010 THE INSTITUTE OF CHARTERED ACCOUNTANTS OF SCOTLAND This document is published by the
More informationThe Artificial Prediction Market
The Artificial Prediction Market Adrian Barbu Department of Statistics Florida State University Joint work with Nathan Lay, Siemens Corporate Research 1 Overview Main Contributions A mathematical theory
More informationIntroduction to Machine Learning Lecture 1. Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu
Introduction to Machine Learning Lecture 1 Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Introduction Logistics Prerequisites: basics concepts needed in probability and statistics
More informationData Analytics in Organisations and Business
Data Analytics in Organisations and Business Dr. Isabelle E-mail: isabelle.flueckiger@math.ethz.ch 1 Data Analytics in Organisations and Business Some organisational information: Tutorship: Gian Thanei:
More informationAgreed-Upon Procedures Engagements
Agreed-Upon Procedures Engagements 1323 AT Section 201 Agreed-Upon Procedures Engagements Source: SSAE No. 10; SSAE No. 11. Effective when the subject matter or assertion is as of or for a period ending
More informationDALLAS COUNTY NON-EXEMPT PERSONNEL PERFORMANCE EVALUATION
DALLAS COUNTY Purpose: The following evaluation form is designed to measure the performance of non-exempt employees during the period of review, and provide an opportunity for the employee and supervisor
More informationRDM on Demand Privacy Policy
RDM on Demand Privacy Policy Ataccama Corp. www.ataccama.com info@ataccama.com Toronto, CA Prague, CZ London, UK Stamford, US 1 ATACCAMA RDM ON DEMAND PRIVACY POLICY 1. Ataccama Corp. ("Ataccama") and
More informationPolicies and Procedures Audit Checklist for HIPAA Privacy, Security, and Breach Notification
Policies and Procedures Audit Checklist for HIPAA Privacy, Security, and Breach Notification Type of Policy and Procedure Comments Completed Privacy Policy to Maintain and Update Notice of Privacy Practices
More information