## Claude Sammut, Achim G. Hoffmann

*Proceedings of the 19th International Conference on Machine Learning*

ICML-2002, 2002.

@proceedings{ICML-2002, address = "Sydney, Australia", editor = "Claude Sammut and Achim G. Hoffmann", isbn = "1-55860-873-7", publisher = "{Morgan Kaufmann}", title = "{Proceedings of the 19th International Conference on Machine Learning}", year = 2002, }

### Contents (87 items)

- ICML-2002-AberdeenB #scalability
- Scalable Internal-State Policy-Gradient Methods for POMDPs (DA, JB), pp. 3–10.
- ICML-2002-AlphonseM #induction #logic programming #set
- Feature Subset Selection and Inductive Logic Programming (ÉA, SM), pp. 11–18.
- ICML-2002-ZubekD #heuristic #learning
- Pruning Improves Heuristic Search for Cost-Sensitive Learning (VBZ, TGD), pp. 19–26.
- ICML-2002-BasuBM #clustering
- Semi-supervised Clustering by Seeding (SB, AB, RJM), pp. 27–34.
- ICML-2002-BianchettiRS #concept #constraints #learning #relational
- Constraint-based Learning of Long Relational Concepts (JAB, CR, MS), pp. 35–42.
- ICML-2002-BockhorstC #concept
- Exploiting Relations Among Concepts to Acquire Weakly Labeled Training Data (JB, MC), pp. 43–50.
- ICML-2002-Bonet #algorithm #markov #process
- An epsilon-Optimal Grid-Based Algorithm for Partially Observable Markov Decision Processes (BB), pp. 51–58.
- ICML-2002-BringmannKNPW
- Transformation-Based Regression (BB, SK, FN, HP, GW), pp. 59–66.
- ICML-2002-ChenWZ #approach #statistics
- A New Statistical Approach to Personal Name Extraction (ZC, LW, FZ), pp. 67–74.
- ICML-2002-ChisholmT #learning #random
- Learning Decision Rules by Randomized Iterative Local Search (MC, PT), pp. 75–82.
- ICML-2002-CrawfordKM #email #named
- IEMS — The Intelligent Email Sorter (EC, JK, EM), pp. 83–90.
- ICML-2002-DashC #classification #naive bayes
- Exact model averaging with naive Bayesian classifiers (DD, GFC), pp. 91–98.
- ICML-2002-DeCoste #classification #distance #geometry #kernel #performance
- Anytime Interval-Valued Outputs for Kernel Machines: Fast Support Vector Machine Classification via Distance Geometry (DD), pp. 99–106.
- ICML-2002-DietterichBMS #learning #probability #refinement
- Action Refinement in Reinforcement Learning by Probability Smoothing (TGD, DB, RLdM, CS), pp. 107–114.
- ICML-2002-DriessensD #learning #relational
- Integrating Experimentation and Guidance in Relational Reinforcement Learning (KD, SD), pp. 115–122.
- ICML-2002-DzeroskiZ #classification
- Is Combining Classifiers Better than Selecting the Best One (SD, BZ), pp. 123–130.
- ICML-2002-ElomaaR #fault #performance
- Fast Minimum Training Error Discretization (TE, JR), pp. 131–138.
- ICML-2002-FerriFH #learning #using
- Learning Decision Trees Using the Area Under the ROC Curve (CF, PAF, JHO), pp. 139–146.
- ICML-2002-FitzgibbonDA #approximate #monte carlo #polynomial
- Univariate Polynomial Inference by Monte Carlo Message Length Approximation (LJF, DLD, LA), pp. 147–154.
- ICML-2002-Gama #analysis #functional
- An Analysis of Functional Trees (JG), pp. 155–162.
- ICML-2002-GambergerL #case study #induction
- Descriptive Induction through Subgroup Discovery: A Case Study in a Medical Domain (DG, NL), pp. 163–170.
- ICML-2002-GargHR #bound #on the
- On generalization bounds, projection profile, and margin distribution (AG, SHP, DR), pp. 171–178.
- ICML-2002-GartnerFKS #kernel #multi
- Multi-Instance Kernels (TG, PAF, AK, AJS), pp. 179–186.
- ICML-2002-Ghani #categorisation #multi
- Combining Labeled and Unlabeled Data for MultiClass Text Categorization (RG), pp. 187–194.
- ICML-2002-GhavamzadehM #learning
- Hierarchically Optimal Average Reward Reinforcement Learning (MG, SM), pp. 195–202.
- ICML-2002-GlobersonT #analysis #novel #reduction
- Sufficient Dimensionality Reduction — A novel Analysis Method (AG, NT), pp. 203–210.
- ICML-2002-GoebelRB #composition #performance #predict
- A Unified Decomposition of Ensemble Loss for Predicting Ensemble Performance (MG, PJR, MB), pp. 211–218.
- ICML-2002-GonzalezHC #concept #graph #learning #relational
- Graph-Based Relational Concept Learning (JAG, LBH, DJC), pp. 219–226.
- ICML-2002-GuestrinLP #coordination #learning
- Coordinated Reinforcement Learning (CG, MGL, RP), pp. 227–234.
- ICML-2002-GuestrinPS #learning #modelling
- Algorithm-Directed Exploration for Model-Based Reinforcement Learning in Factored MDPs (CG, RP, DS), pp. 235–242.
- ICML-2002-Hengst #learning
- Discovering Hierarchy in Reinforcement Learning with HEXQ (BH), pp. 243–250.
- ICML-2002-Ho #classification
- Classification Value Grouping (CKMH), pp. 251–258.
- ICML-2002-JensenN #bias #feature model #learning #relational
- Linkage and Autocorrelation Cause Feature Selection Bias in Relational Learning (DJ, JN), pp. 259–266.
- ICML-2002-KakadeL #approximate #learning
- Approximately Optimal Approximate Reinforcement Learning (SK, JL), pp. 267–274.
- ICML-2002-KakadeTR #markov
- An Alternate Objective Function for Markovian Fields (SK, YWT, STR), pp. 275–282.
- ICML-2002-KamvarKM #algorithm #approach #clustering #modelling #using
- Interpreting and Extending Classical Agglomerative Clustering Algorithms using a Model-Based approach (SDK, DK, CDM), pp. 283–290.
- ICML-2002-KashimaK #kernel
- Kernels for Semi-Structured Data (HK, TK), pp. 291–298.
- ICML-2002-KeerthiDSP #algorithm #kernel #performance
- A Fast Dual Algorithm for Kernel Logistic Regression (SSK, KD, SKS, ANP), pp. 299–306.
- ICML-2002-KleinKM #clustering #constraints #information management
- From Instance-level Constraints to Space-Level Constraints: Making the Most of Prior Knowledge in Data Clustering (DK, SDK, CDM), pp. 307–314.
- ICML-2002-KondorL #graph #kernel
- Diffusion Kernels on Graphs and Other Discrete Input Spaces (RK, JDL), pp. 315–322.
- ICML-2002-LanckrietCBGJ #kernel #learning #matrix #programming
- Learning the Kernel Matrix with Semi-Definite Programming (GRGL, NC, PLB, LEG, MIJ), pp. 323–330.
- ICML-2002-Langford #bound #testing
- Combining Trainig Set and Test Set Bounds (JL), pp. 331–338.
- ICML-2002-LangfordZK #analysis #trade-off
- Competitive Analysis of the Explore/Exploit Tradeoff (JL, MZ, SK), pp. 339–346.
- ICML-2002-LangleySTD #modelling #process
- Inducing Process Models from Continuous Data (PL, JNS, LT, SD), pp. 347–354.
- ICML-2002-LaudD #behaviour #learning
- Reinforcement Learning and Shaping: Encouraging Intended Behaviors (AL, GD), pp. 355–362.
- ICML-2002-LebanonL #modelling #named #permutation #probability #ranking #using
- Cranking: Combining Rankings Using Conditional Probability Models on Permutations (GL, JDL), pp. 363–370.
- ICML-2002-LeckieR #distributed #learning #probability
- Learning to Share Distributed Probabilistic Beliefs (CL, KR), pp. 371–378.
- ICML-2002-LiZHSK #algorithm
- The Perceptron Algorithm with Uneven Margins (YL, HZ, RH, JST, JSK), pp. 379–386.
- ICML-2002-LiuLYL #classification #documentation
- Partially Supervised Classification of Text Documents (BL, WSL, PSY, XL), pp. 387–394.
- ICML-2002-LiuMY #feature model
- Feature Selection with Selective Sampling (HL, HM, LY), pp. 395–402.
- ICML-2002-LuPS
- Investigating the Maximum Likelihood Alternative to TD(λ) (FL, RP, DS), pp. 403–410.
- ICML-2002-MerkeS #approximate #convergence #learning
- A Necessary Condition of Convergence for Reinforcement Learning with Function Approximation (AM, RS), pp. 411–418.
- ICML-2002-MeyerB #scalability #speech #towards
- Towards “Large Margin” Speech Recognizers by Boosting and Discriminative Training (CM, PB), pp. 419–426.
- ICML-2002-Mladenic #learning #normalisation #using #word
- Learning word normalization using word suffix and context from unlabeled data (DM), pp. 427–434.
- ICML-2002-MusleaMK #learning #multi #robust
- Active + Semi-supervised Learning = Robust Multi-View Learning (IM, SM, CAK), pp. 435–442.
- ICML-2002-MusleaMK02a #adaptation #automation #detection #towards #validation
- Adaptive View Validation: A First Step Towards Automatic View Detection (IM, SM, CAK), pp. 443–450.
- ICML-2002-OLZ #learning #using
- Stock Trading System Using Reinforcement Learning with Cooperative Agents (JO, JWL, BTZ), pp. 451–458.
- ICML-2002-OatesDB #context-free grammar #learning
- Learning k-Reversible Context-Free Grammars from Positive Structural Examples (TO, DD, VB), pp. 459–465.
- ICML-2002-OliverG #markov #modelling #named
- MMIHMM: Maximum Mutual Information Hidden Markov Models (NO, AG), pp. 466–473.
- ICML-2002-PanangadanD #2d #correlation #learning #navigation
- Learning Spatial and Temporal Correlation for Navigation in a 2-Dimensional Continuous World (AP, MGD), pp. 474–481.
- ICML-2002-ParkZ #learning
- A Boosted Maximum Entropy Model for Learning Text Chunking (SBP, BTZ), pp. 482–489.
- ICML-2002-PerkinsP #fixpoint #on the
- On the Existence of Fixed Points for Q-Learning and Sarsa in Partially Observable Domains (TJP, MDP), pp. 490–497.
- ICML-2002-PeshkinS #experience #learning
- Learning from Scarce Experience (LP, CRS), pp. 498–505.
- ICML-2002-PickettB #algorithm #learning #named
- PolicyBlocks: An Algorithm for Creating Useful Macro-Actions in Reinforcement Learning (MP, AGB), pp. 506–513.
- ICML-2002-RaskuttiFK #classification #clustering #parametricity #using
- Using Unlabelled Data for Text Classification through Addition of Cluster Parameters (BR, HLF, AK), pp. 514–521.
- ICML-2002-Ryan #automation #behaviour #learning #modelling #using
- Using Abstract Models of Behaviours to Automatically Generate Reinforcement Learning Hierarchies (MRKR), pp. 522–529.
- ICML-2002-SaundersTS #kernel #string
- Syllables and other String Kernel Extensions (CS, HT, JST), pp. 530–537.
- ICML-2002-SchapireRRG #information management
- Incorporating Prior Knowledge into Boosting (RES, MR, MGR, NKG), pp. 538–545.
- ICML-2002-SchapireSMLC #estimation #modelling #nondeterminism #using
- Modeling Auction Price Uncertainty Using Boosting-based Conditional Density Estimation (RES, PS, DAM, MLL, JAC), pp. 546–553.
- ICML-2002-Seewald #how #performance
- How to Make Stacking Better and Faster While Also Taking Care of an Unknown Weakness (AKS), pp. 554–561.
- ICML-2002-SeriT #learning #modelling
- Model-based Hierarchical Average-reward Reinforcement Learning (SS, PT), pp. 562–569.
- ICML-2002-ShapiroL #learning #using
- Separating Skills from Preference: Using Learning to Program by Reward (DGS, PL), pp. 570–577.
- ICML-2002-SlonimBFT #feature model #markov #memory management #multi
- Discriminative Feature Selection via Multiclass Variable Memory Markov Model (NS, GB, SF, NT), pp. 578–585.
- ICML-2002-Stirling #learning
- Learning to Fly by Controlling Dynamic Instabilities (DS), pp. 586–593.
- ICML-2002-StracuzziU #random
- Randomized Variable Elimination (DJS, PEU), pp. 594–601.
- ICML-2002-StrensBE #markov #monte carlo #optimisation #using
- Markov Chain Monte Carlo Sampling using Direct Search Optimization (MJAS, MB, NE), pp. 602–609.
- ICML-2002-SucB #reverse engineering
- Qualitative reverse engineering (DS, IB), pp. 610–617.
- ICML-2002-TakechiS #induction
- Finding an Optimal Gain-Ratio Subset-Split Test for a Set-Valued Attribute in Decision Tree Induction (FT, ES), pp. 618–625.
- ICML-2002-TeowLNY #approach #fault #feature model
- Refining the Wrapper Approach — Smoothed Error Estimates for Feature Selection (LNT, HL, HTN, EY), pp. 626–633.
- ICML-2002-ThamDR #classification #learning #markov #monte carlo #using
- Sparse Bayesian Learning for Regression and Classification using Markov Chain Monte Carlo (SST, AD, KR), pp. 634–641.
- ICML-2002-Ting #classification #evaluation #using
- Issues in Classifier Evaluation using Optimal Cost Curves (KMT), pp. 642–649.
- ICML-2002-WangW #modelling #predict #probability
- Modeling for Optimal Probability Prediction (YW, IHW), pp. 650–657.
- ICML-2002-WuZZ #mining
- Mining Both Positive and Negative Association Rules (XW, CZ, SZ), pp. 658–665.
- ICML-2002-YangW #classification
- Non-Disjoint Discretization for Naive-Bayes Classifiers (YY, GIW), pp. 666–673.
- ICML-2002-ZhangL #bound #network
- Representational Upper Bounds of Bayesian Networks (HZ, CXL), pp. 674–681.
- ICML-2002-ZhangGYF #image #learning #multi #retrieval #using
- Content-Based Image Retrieval Using Multiple-Instance Learning (QZ, SAG, WY, JEF), pp. 682–689.
- ICML-2002-Zhang #behaviour #consistency #statistics
- Statistical Behavior and Consistency of Support Vector Machines, Boosting, and Beyond (TZ0), pp. 690–700.

31 ×#learning

13 ×#using

9 ×#classification

9 ×#modelling

7 ×#kernel

6 ×#markov

5 ×#algorithm

5 ×#multi

5 ×#performance

4 ×#clustering

13 ×#using

9 ×#classification

9 ×#modelling

7 ×#kernel

6 ×#markov

5 ×#algorithm

5 ×#multi

5 ×#performance

4 ×#clustering