Fighting Knowledge Acquisition Bottleneck

Slides:



Advertisements
Similar presentations
Explanation-Based Learning (borrowed from mooney et al)
Advertisements

ABML K NOWLEDGE R EFINEMENT L OOP A C ASE S TUDY Matej Guid, Martin Možina Vida Groznik, Aleksander Sadikov, Ivan Bratko Artificial Intelligence Laboratory.
Deriving Concepts and Strategies from Chess Tablebases Matej Guid, Martin Možina, Aleksander Sadikov, and Ivan Bratko Faculty of Computer and Information.
D ESIGNING AN I NTERACTIVE T EACHING T OOL WITH ABML K NOWLEDGE R EFINEMENT L OOP enabling arguing to learn 1 Faculty of Education, University of Ljubljana,
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Rulebase Expert System and Uncertainty. Rule-based ES Rules as a knowledge representation technique Type of rules :- relation, recommendation, directive,
Learning Positional Features for Annotating Chess Games: A Case Study Matej Guid, Martin Mozina, Jana Krivec, Aleksander Sadikov and Ivan Bratko CG 2008.
Discourse Analysis of Students’ Research Papers Roman Taraban Texas Tech University July 2010.
Computation and representation Joe Lau. Overview of lecture What is computation? Brief history Computational explanations in cognitive science Levels.
Adversarial Search Chapter 5.
Decision Tree Learning 主講人:虞台文 大同大學資工所 智慧型多媒體研究室.
Active subgroup mining for descriptive induction tasks Dragan Gamberger Rudjer Bošković Instute, Zagreb Zdenko Sonicki University of Zagreb.
SBSE Course 3. EA applications to SE Analysis Design Implementation Testing Reference: Evolutionary Computing in Search-Based Software Engineering Leo.
Integrating Bayesian Networks and Simpson’s Paradox in Data Mining Alex Freitas University of Kent Ken McGarry University of Sunderland.
Decision Tree Rong Jin. Determine Milage Per Gallon.
LEARNING FROM OBSERVATIONS Yılmaz KILIÇASLAN. Definition Learning takes place as the agent observes its interactions with the world and its own decision-making.
Relational Data Mining in Finance Haonan Zhang CFWin /04/2003.
LEARNING FROM OBSERVATIONS Yılmaz KILIÇASLAN. Definition Learning takes place as the agent observes its interactions with the world and its own decision-making.
ML ALGORITHMS. Algorithm Types Classification (supervised) Given -> A set of classified examples “instances” Produce -> A way of classifying new examples.
Factors Affecting Diminishing Returns for Searching Deeper Matej Guid and Ivan Bratko CGW 2007.
G OAL -O RIENTED C ONCEPTUALIZATION OF P ROCEDURAL K NOWLEDGE Martin Možina, Matej Guid, Aleksander Sadikov, Vida Groznik, Ivan Bratko Artificial Intelligence.
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
Educator’s Guide Using Instructables With Your Students.
Copyright R. Weber Machine Learning, Data Mining ISYS370 Dr. R. Weber.
Introduction to variable selection I Qi Yu. 2 Problems due to poor variable selection: Input dimension is too large; the curse of dimensionality problem.
COMP3503 Intro to Inductive Modeling
1 Machine Learning: Lecture 11 Analytical Learning / Explanation-Based Learning (Based on Chapter 11 of Mitchell, T., Machine Learning, 1997)
Qualitative Induction Dorian Šuc and Ivan Bratko Artificial Intelligence Laboratory Faculty of Computer and Information Science University of Ljubljana,
Prepared by : Walaa Maqdasawi Razan Jararah Supervised by: Dr. Aladdin Masri.
Kansas State University Department of Computing and Information Sciences CIS 830: Advanced Topics in Artificial Intelligence Friday, February 4, 2000 Lijun.
ASSESSING LEARNING ALGORITHMS Yılmaz KILIÇASLAN. Assessing the performance of the learning algorithm A learning algorithm is good if it produces hypotheses.
AI Week 14 Machine Learning: Introduction to Data Mining Lee McCluskey, room 3/10
Exploiting Context Analysis for Combining Multiple Entity Resolution Systems -Ramu Bandaru Zhaoqi Chen Dmitri V.kalashnikov Sharad Mehrotra.
Ensemble Learning Spring 2009 Ben-Gurion University of the Negev.
Senior Project Poster Day 2007, CIS Dept. University of Pennsylvania Reversi Meng Tran Faculty Advisor: Dr. Barry Silverman Strategies: l Corners t Corners.
Machine Learning Chapter 5. Artificial IntelligenceChapter 52 Learning 1. Rote learning rote( โรท ) n. วิถีทาง, ทางเดิน, วิธีการตามปกติ, (by rote จากความทรงจำ.
Detecting Group Differences: Mining Contrast Sets Author: Stephen D. Bay Advisor: Dr. Hsu Graduate: Yan-Cheng Lin.
ASSESSING LEARNING ALGORITHMS Yılmaz KILIÇASLAN. Assessing the performance of the learning algorithm A learning algorithm is good if it produces hypotheses.
ASSESSING LEARNING ALGORITHMS Yılmaz KILIÇASLAN. Assessing the performance of the learning algorithm A learning algorithm is good if it produces hypotheses.
Ensemble Methods in Machine Learning
CpSc 810: Machine Learning Analytical learning. 2 Copy Right Notice Most slides in this presentation are adopted from slides of text book and various.
Data Mining and Decision Support
CSC 8520 Spring Paula Matuszek DecisionTreeFirstDraft Paula Matuszek Spring,
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
Machine Learning in Practice Lecture 2 Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
A Heuristic Hillclimbing Algorithm for Mastermind Alexandre Temporel and Tim Kovacs.
Naïve Bayes Classifier April 25 th, Classification Methods (1) Manual classification Used by Yahoo!, Looksmart, about.com, ODP Very accurate when.
CSE573 Autumn /09/98 Machine Learning Administrative –Last topic: Decision Tree Learning Reading: 5.1, 5.4 Last time –finished NLP sample system’s.
Machine Learning: Ensemble Methods
Game Playing Why do AI researchers study game playing?
CS 9633 Machine Learning Explanation Based Learning
Who am I? Work in Probabilistic Machine Learning Like to teach 
Influence of Search Depth on Position Evaluation
D1 Miwa Makoto Chikayama & Taura Lab
CACTUS-Clustering Categorical Data Using Summaries
An Artificial Intelligence Approach to Precision Oncology
CS 9633 Machine Learning Concept Learning
AF1: Thinking Scientifically
Reading: Pedro Domingos: A Few Useful Things to Know about Machine Learning source: /cacm12.pdf reading.
Classroom test and Assessment
Machine Learning Basics
ECE 5424: Introduction to Machine Learning
Adaboost Team G Youngmin Jun
Data Mining Practical Machine Learning Tools and Techniques
Learning with Identification Trees
Cos 429: Face Detection (Part 2) Viola-Jones and AdaBoost Guest Instructor: Andras Ferencz (Your Regular Instructor: Fei-Fei Li) Thanks to Fei-Fei.
Machine Learning: Lecture 3
CS Fall 2016 (Shavlik©), Lecture 2
Machine learning overview
A handbook on validation methodology. Metrics.
Presentation transcript:

Fighting Knowledge Acquisition Bottleneck ECAI 2008 Fighting Knowledge Acquisition Bottleneck with Argument Based Machine Learning Martin Mozina, Matej Guid, Jana Krivec, Aleksander Sadikov and Ivan Bratko Faculty of Computer and Information Science University of Ljubljana, Slovenia

Motivation for Knowledge Acquisition with Argument Based Machine Learning Knowledge Acquisition is a major bottleneck in building knowledge bases. domain experts find it hard to articulate their knowledge Machine Learning is a potential solution, but has weaknesses Machine Learning & Knowledge Acquisition Problem: Models are not comprehensible to domain experts mostly statistical learning (not symbolic) inducing spurious concepts (e.g. overfitting) Combination of domain expert and machine learning would yield best results learn symbolic models exploit experts’ knowledge in learning

Combining Machine Learning and Expert Knowledge Expert provides background knowledge for ML Expert validates and revises induced theory Iterative procedure: Experts and ML improve the model in turns IF ... THEN ... ...

Combining Machine Learning and Expert Knowledge Expert provides background knowledge for ML Expert validates and revises induced theory Iterative procedure: Experts and ML improve the model in turns IF ... THEN ... ...

Combining Machine Learning and Expert Knowledge Expert provides background knowledge for ML Expert validates and revises induced theory Iterative procedure: Experts and ML improve the model in turns IF ... THEN ... ... ABML

Definition of Argument Based Machine Learning Learning with background knowledge: INPUT: learning examples E, background knowledge BK OUTPUT: theory T, T and BK explain all ei from E Argument Based Machine Learning: INPUT: learning examples E, arguments ai given to ei (from E) OUTPUT: theory T, T explains ei with arguments ai BK,T ei T ei ai

Argument Based Rule Learning Name RegularJob Rich AccountStatus HairColor CreditApproved Mr. Bond No Yes Negative Blond Mr. Grey Positive Grey Miss White Miss Silver Mrs. Brown Brown Name RegularJob Rich AccountStatus HairColor CreditApproved Mr. Bond No Yes Negative Blond Mr. Grey Positive Grey Miss White Miss Silver Mrs. Brown Brown Name RegularJob Rich AccountStatus HairColor CreditApproved Mr. Bond No Yes Negative Blond Mr. Grey Positive Grey Miss White Miss Silver Mrs. Brown Brown Name RegularJob Rich AccountStatus HairColor CreditApproved Mr. Bond No Yes Negative Blond Mr. Grey Positive Grey Miss White Miss Silver Mrs. Brown Brown Classic rule learning: IF HairColor = Blond THEN CreditApproved = YES Possible argument: Miss White received credit (CreditApproved=YES) because she has a regular job (RegularJob=YES). AB rule learning (possible rule): IF RegularJob=YES AND AccountStatus = Positive THEN CreditApproved = YES

Formal definition of Argumented Examples Argumented Example (A, C, Arguments): A; attribute-value vector [e.g. RegularJob=YES,Rich=NO, ...] C; class value [e.g. CreditApproved=YES] Arguments; a set of arguments Arg1, ..., Argn for this example Argument Argi : Positive argument: C because Reasons Negative Argument: C despite Reasons Reasons: a conjunction of reasons r1, ..., rm

ABCN2 ABCN2 = extension of CN2 rule learning algorithm (Clark,Niblett 1991) Extensions: Argument Based covering: All conditions in R are true for E R is consistent with at least one positive argument of E. R is not consistent with any negative argument of E. Evaluation: Extreme Value Correction (Mozina et al. 2006) Probabilistic covering (required for Extreme Value Correction)

Interactions between expert and ABML learn data set Learn a hypothesis with ABML. Find the most critical example. (if none found, stop procedure) Expert explains the example. Argument is added to the example. Return to step 1. Argument ABML critical example What if expert’s explanation is not good enough?

Interactions between expert and ABML Expert explains example. Add argument to example Discover counter examples (if none, then stop). Expert improves the argument for example. Return to step 3. Learn a hypothesis with ABML. Find the most critical example. (if none found, stop procedure) Expert explains the example. Argument is added to the example. Return to step 1. What if expert’s explanation is not good enough?

Knowledge Acquisition of Chess Concepts used in a Chess Tutoring Application Case Study: Bad Bishop

The Concept of the Bad Bishop Chess experts in general understand the concept of bad bishop. Precise formalisation of this concept is difficult. Traditional definition (John Watson, Secrets of Modern Chess Strategy, 1999) A bishop that is on the same colour of squares as its own pawns is bad: its mobility is restricted by its own pawns, it does not defend the squares in front of these pawns. Moreover, centralisation of these pawns is the main factor in deciding whether the bishop is bad or not.

Data set Data set: 200 middlegame positions from real chess games Chess experts’ evaluation of bishops: bad: 78 bishops not bad: 122 bishops wGM Jana Krivec GM Garry Kasparov FM Matej Guid We randomly selected: 100 positions for learning 100 positions for testing CRAFTY’s positional feature values served as attribute values for learning.

Standard Machine Learning Methods' Performance with CRAFTY's features only Machine learning methods’ performance on initial dataset Method CA Brier score AUC Decision trees (C4.5) 73% 0,49 0,74 Logistic regression 70% 0,43 0,84 Rule learning (CN2) 72% 0,39 0,80 The results were obtained on test data set. The results obtained with CRAFTY’s positional features only are too inaccurate for commenting purposes… additional information for describing bad bishops is necessary.

First Critical Example Rules obtained by ABML method ABCN2 failed to classify this example as "not bad" The following question was given to the experts: “Why is the black bishop not bad?“ The experts used their domain knowledge: “The black bishop is not bad, since its mobility is not seriously restricted by the pawns of both players.”

Introducing new attributes into the domain and adding arguments to an example Experts’ explanation could not be described with current domain attributes. A new attribute, IMPROVED_BISHOP_MOBILITY, was included into the domain: the number of squares accessible to the bishop, taking into account only own and opponent’s pawn structure The argument “BISHOP=“not bad” because IMPROVED_BISHOP_MOBILITY is high“ was added to the example.

Counter example Method failed to explain critical example with given argument. Counter example was presented to experts: Critical example: “not bad”, IMPROVED_BISHOP_MOBILITY is high. Counter example: “bad”, although IMPROVED_BISHOP_MOBILITY is high. "Why is the “red” bishop bad, comparing to the “green” one?" Experts’ explanation: “There are many pawns on the same colour of squares as the black bishop, and some of these pawns occupy the central squares.”

Improving Arguments with Counter Examples Attribute BAD_PAWNS was included into the domain. This attribute evaluates pawns that are on the colour of the square of the bishop ("bad" pawns in this sense). The argument given to the critical example was extended to “BISHOP=“not bad” because IMPROVED_BISHOP_MOBILITY is high and BAD_PAWNS is low” With this argument the method could not find any counter examples anymore. New rule: if IMPROVED_BISHOP_MOBILITY ≥ 4 and BAD_PAWNS ≤ 32 then BISHOP= “not bad” class distribution [0,39]

Assesing “bad” pawns The experts designed a look-up table (left) with predefined values for the pawns that are on the color of the square of the bishop in order to assign weights to such pawns. BAD_PAWNS_AHEAD = 16 + 24 + 2 = 42

After the Final Iteration... The whole process consisted of 8 iterations. 7 arguments were attached to automatically selected critical examples 5 new attributes were included into the domain Attribute Description BAD_PAWNS pawns on the color of the square of the bishop - weighted according to their squares (bad pawns)  BAD_PAWNS_AHEAD  bad pawns ahead of the bishop BAD_PAWNS _BLOCK_BISHOP_DIAGONAL bad pawns that block the bishop's (front) diagonals  BLOCKED_BAD_PAWNS  bad pawns blocked by opponent's pawns or pieces  IMPROVED_BISHOP_MOBILITY  number of squares accessible to the bishop taking into account only pawns of both opponents 

Classification Accuracy Through Iterations Results on the final dataset Method CA Brier score AUC Decision trees (C4.5) 89% 0,21 0,86 Logistic regression 88% 0,19 0,96 Rule learning (CN2) 0,94 ABCN2 95% 0,11 0,97

Classification Accuracy Through Iterations The accuracies of all methods improved by adding new attributes. ABCN2 (which also used the arguments) outperformed all others. Arguments suggested useful attributes AND lead to even more accurate models.

Advantages of ABML for Knowledge Acquisition explain single example easier for experts to articulate knowledge more knowledge from experts critical examples expert provide only relevant knowledge time of experts' involvent is decreased

Advantages of ABML for Knowledge Acquisition counter examples detect deficiencies in expert's explanations even more knowledge from experts arguments constrain learning hypotheses are consistent with expert knowledge hypotheses comprehensible to expert more accurate hypotheses

Argument Based Machine Learning better knowledge acquisition Conclusions ABML-based Knowledge Acquisition process provides: more knowledge from experts time of experts' involvent is decreased hypotheses comprehensible to expert more accurate hypotheses Argument Based Machine Learning enables better knowledge acquisition