Artificial Intelligence MEI 2008/2009 Bruno Paulette.

Slides:



Advertisements
Similar presentations
Lecture 3: CBR Case-Base Indexing
Advertisements

Lecture 5: Reuse, Adaptation and Retention
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
Machine Learning Instance Based Learning & Case Based Reasoning Exercise Solutions.
Inferences The Reasoning Power of Expert Systems.
Lazy vs. Eager Learning Lazy vs. eager learning
Application of Inductive Learning and Case-Based Reasoning for Troubleshooting Industrial Machines - Michel Manago and Eric Auriol 컴퓨터공학과 신수용.
Navneet Goyal. Instance Based Learning  Rote Classifier  K- nearest neighbors (K-NN)  Case Based Resoning (CBR)
Artificial Intelligence and Case-Based Reasoning Computer Science and Engineering Mälardalen University Västerås, Mikael Sollenborn, CSL,
SESSION 10 MANAGING KNOWLEDGE FOR THE DIGITAL FIRM.
Chapter Physical Database Design Methodology Software & Hardware Mapping Logical Design to DBMS Physical Implementation Security Implementation Monitoring.
1999/3/10Li-we Pan1 Case-Based CBR : Capturing and Reusing Reasoning About Case Adaptation 指導老師 : 何正信教授 學生:潘立偉 學號: M 日期: 88/3/10 David B. Leake,
Case Based Reasoning Melanie Hanson Engr 315. What is Case-Based Reasoning? Storing information from previous experiences Using previously gained knowledge.
1 Episodic Memory for Soar Agents Andrew Nuxoll 11 June 2004.
Basic Data Mining Techniques
Case-based Reasoning System (CBR)
Learning from Experience: Case Injected Genetic Algorithm Design of Combinational Logic Circuits Sushil J. Louis Genetic Algorithm Systems Lab(gaslab)
Marakas: Decision Support Systems, 2nd Edition © 2003, Prentice-Hall Chapter Chapter 7: Expert Systems and Artificial Intelligence Decision Support.
Case-based reasoning.
Instance Based Learning Bob Durrant School of Computer Science University of Birmingham (Slides: Dr Ata Kabán) 1.
Building Knowledge-Driven DSS and Mining Data
Extracting Test Cases by Using Data Mining; Reducing the Cost of Testing Andrea Ciocca COMP 587.
A Web-based Intelligent Hybrid System for Fault Diagnosis Gunjan Jha Research Student Nanyang Technological University Singapore.
Intelligent Systems for Decision Support
Becerra-Fernandez, et al. -- Knowledge Management 1/e -- © 2004 Prentice Hall Chapter 16 Knowledge Application Systems: Systems that Utilize Knowledge.
By: M.Nadeem Akhtar1 The Data Base Management System (DBMS) Ch # 09.
Copyright R. Weber Machine Learning, Data Mining ISYS370 Dr. R. Weber.
Case-Based Recommendation Presented by Chul-Hwan Lee Barry Smyth.
Taxonomy of Problem Solving and Case-Based Reasoning (CBR)
CBR for Design Upmanyu Misra CSE 495. Design Research Develop tools to aid human designers Automate design tasks Better understanding of design Increase.
9/14/2012ISC329 Isabelle Bichindaritz1 Database System Life Cycle.
Becerra-Fernandez, et al. -- Knowledge Management 1/e -- © 2004 Prentice Hall Chapter 9 Using Past History Explicitly as Knowledge: Case-based Reasoning.
Case-based Reasoning A type of analogical reasoning
CBR for Fault Analysis in DAME Max Ong University of Sheffield.
Decision Trees & the Iterative Dichotomiser 3 (ID3) Algorithm David Ramos CS 157B, Section 1 May 4, 2006.
CS 682, AI:Case-Based Reasoning, Prof. Cindy Marling1 Chapter 3: Reasoning Using Cases In this chapter, we look at how cases are used to reason We’ve already.
Introduction To System Analysis and Design
GATree: Genetically Evolved Decision Trees 전자전기컴퓨터공학과 데이터베이스 연구실 G 김태종.
K Nearest Neighbors Saed Sayad 1www.ismartsoft.com.
Some working definitions…. ‘Data Mining’ and ‘Knowledge Discovery in Databases’ (KDD) are used interchangeably Data mining = –the discovery of interesting,
Tutoring and Help Systems Tell me and I forget. Show me and I remember. Involve me and I understand. - Chinese proverb.
Configuration Systems - CSE Sudhan Kanitkar.
Case study of Several Case Based Reasoners Sandesh.
1 Instance Based Learning Ata Kaban The University of Birmingham.
I Robot.
March 1999Dip HI KBS1 Knowledge-based Systems Alternatives to Rules.
CS 682, AI:Case-Based Reasoning, Prof. Cindy Marling1 Chapter 11: Adaptation Methods and Strategies Adaptation is the process of modifying a close, but.
Knowledge Learning by Using Case Based Reasoning (CBR)
Strategies for Distributed CBR Santi Ontañón IIIA-CSIC.
1 Knowledge Acquisition and Learning by Experience – The Role of Case-Specific Knowledge Knowledge modeling and acquisition Learning by experience Framework.
CpSc 881: Machine Learning Instance Based Learning.
AI in Knowledge Management Professor Robin Burke CSC 594.
CpSc 810: Machine Learning Instance Based Learning.
Data Mining: Knowledge Discovery in Databases Peter van der Putten ALP Group, LIACS Pre-University College Bio Informatics January
20. september 2006TDT55 - Case-based reasoning1 Retrieval, reuse, revision, and retention in case-based reasoning.
An Introduction Student Name: Riaz Ahmad Program: MSIT( ) Subject: Data warehouse & Data Mining.
Data Mining and Decision Support
Artificial Intelligence
CS Machine Learning Instance Based Learning (Adapted from various sources)
Principles in the Evolutionary Design of Digital Circuits J. F. Miller, D. Job, and V. K. Vassilev Genetic Programming and Evolvable Machines.
Kansas State University Department of Computing and Information Sciences CIS 890: Special Topics in Intelligent Systems Wednesday, November 15, 2000 Cecil.
Developing a diagnostic system through integration of fuzzy case-based reasoning and fuzzy ant colony system Expert Systems with Applications 28(2005)
Spatial Approximate String Search. Abstract This work deals with the approximate string search in large spatial databases. Specifically, we investigate.
Architecture Components
Case-Based Reasoning CBR Cycle CBR Problem Issues
Case-Based Reasoning.
Taxonomy of Problem Solving and Case-Based Reasoning (CBR)
Case-Based Reasoning BY: Jessica Jones CSCI 446.
Lecture 6: Knowledge Application Systems
Presentation transcript:

Artificial Intelligence MEI 2008/2009 Bruno Paulette

Index What is Case-Based Reasoning? Interaction between CBR and Nature Diferences between CBR and RBS Cased-Based Systems CBR cycle

Index Case-Based Reasoning Techniques Case representation Indexing Storage Retrieval Adaptation

What is Case-based Reasoning? Example: Bank A bank manager, based on information provided by clients, like monthly income, job status, and others study if the bank should grant a loan of a amount or money, for that he must know, if it is likely or not, that the client will repay the loan. The bank employee has access to previous loans and their outputs

What is Case-based Reasoning? Experiences Problems Experiences Good or Bad – but always important Why they are important? Move forward – Evolve Knowledge

Differences between CBR and RBS For building an rule based system, it is necessary first to know how to address the problem RBS aren’t capable of outputting a solution based on past experiences (they don’t have any memory) If a problem was solved in the past, in RBS it will have to be solved again

Differences between CBR and RBS We can adapt old problems to solve new ones Useful when we have a good set of resolved cases Knowledge representation is dynamic Representation of experiences Cases

How to apply CBR? Databases Problem Solution DATABASE Problem Description If we use databases we could store Problems descriptions along with Solutions in a Database

Problems with this representation However in Databases The problem may not present itself in the same manner that is stored in databases Databases make exact matching; CBR requires approximate matching - we want to be able to find SIMILAR problems.

Case-Based Cycle “A Case Based reasoner solves new problems by adapting solutions that were used to solve old problems” Riesbieck and Schank, 1989

Case-Based Cycle Problem Analyze Proposed Solution Confirmed Solution Case- Base Revise ReuseRetain Retrieve

Case-Based Reasoning Techniques Case Representation A case is a contextualized piece of knowledge A case represents a experience The cases are: Historical Developed by an expert in the domain

Case-Based Reasoning Techniques The problem and solution spaces

Case-Based Reasoning Techniques Indexing Indexes are used frequently by databases, to speedup the data retrieving CBR also use indexes to speedup retrieval

Case-Based Reasoning Techniques Ref: 1423 Patient Name: Peter Pan Address: Never Land Photo: Age: eternal child Sex: Male Weight: 40 kg Height: 1,50m Blood Type: “Red” } } Unindexed features Indexed features Information that can be used for retrieval Information that may provide contextual information of value to the user

Case-Based Reasoning Techniques Storage Important aspect in to design efficient CBR systems. Represents conceptual view that represents the case. Choose the indexes that characterize the case. The case-base organized in a structure that supports efficient search and retrieval methods.

Case-Based Reasoning Techniques Retrieval Two techniques are used for case retrieval Nearest-Neighbor Retrieval Inductive Retrieval

Case-Based Reasoning Techniques Example: Bank A bank manager, based on information provided by clients, like monthly income, job status, and others study if the bank should grant a loan of a amount or money, for that he must know, if it is likely or not, that the client will repay the loan. The bank employee has access to previous loans and their outputs

Nearest-Neighbor Retrieval Case Indexes Monthly income Monthly loan repayment Case Result Good loanBad loan Monthly Income Monthly loan repayment

Nearest-Neighbor Retrieval Monthly Income Monthly loan repayment Bad Loans Good Loans New Case

Nearest-Neighbor Retrieval Similarity A is the target case B is the source case n is the number of attributes in each case I is an individual attribute from 1 to n f is a similarity function from attribute i W is the importance weighting of attribute i

Inductive Retrieval The case base is analyzed An induction algorithm is used to build a decision tree This decision tree classifies (or indexes) the cases The most widely used induction algorithm is ID3

Inductive Retrieval Loan status Monthly Income Job StatusRepayment Case 1Good2,000Salaried 200 Case 2Very bad4,000Salaried 600 Case 3Very good5,000Waged 300 Case 4Bad1,500Salaried 200 Repayment < 4000 Income > 1500 Case 1 Job Status Case 3Case 2Case 4 Good LoansBad Loans YesNo Yes SalariedWaged

Case-Based Reasoning Techniques Adaptation Types: None Structural Adapts rules or formulas directly to the solution stored cases Derivational Reuses the rules or formulas that generated the original solution to produce a new solution to the current problem

Bibliography Watson, Cap. 1, 2; Presentations from the last years.

Questions & Doubts