William W. Cohen, Haym Hirsh
Proceedings of the 11th International Conference on Machine Learning
ICML, 1994.

@proceedings{ICML-1994,
	address       = "New Brunswick, New Jersey, USA",
	editor        = "William W. Cohen and Haym Hirsh",
	isbn          = "1-55860-335-2",
	publisher     = "{Morgan Kaufmann}",
	title         = "{Proceedings of the 11th International Conference on Machine Learning}",
	year          = 1994,
}

Contents (45 items)

14 ×#learning
8 ×#algorithm
5 ×#incremental
5 ×#induction
3 ×#logic programming
3 ×#performance
3 ×#search-based
2 ×#approach
2 ×#architecture
2 ×#concept

ICML-1994-AbeM #predict #probability

A New Method for Predicting Protein Secondary Structures Based on Stochastic Tree Grammars (NA, HM), pp. 3–11.

ICML-1994-AhaLLM #learning #recursion #set

Learning Recursive Relations with Randomly Selected Small Training Sets (DWA, SL, CXL, SM), pp. 12–18.

ICML-1994-Asker

Improving Accuracy of Incorrect Domain Theories (LA), pp. 19–27.

ICML-1994-CaruanaF

Greedy Attribute Selection (RC, DF), pp. 28–36.

ICML-1994-CravenS #network #query #using

Using Sampling and Queries to Extract Rules from Trained Neural Networks (MC, JWS), pp. 37–45.

ICML-1994-Maza #architecture

The Generate, Test, and Explain Discovery System Architecture (MdlM), pp. 46–52.

ICML-1994-DruckerCJCV #algorithm #machine learning

Boosting and Other Machine Learning Algorithms (HD, CC, LDJ, YL, VV), pp. 53–61.

ICML-1994-Elomaa #learning

In Defense of C4.5: Notes Learning One-Level Decision Trees (TE), pp. 62–69.

ICML-1994-FurnkranzW #fault #incremental

Incremental Reduced Error Pruning (JF, GW), pp. 70–77.

ICML-1994-GervasioD #approach #incremental #learning

An Incremental Learning Approach for Completable Planning (MTG, GD), pp. 78–86.

ICML-1994-Gil #incremental #learning #refinement

Learning by Experimentation: Incremental Refinement of Incomplete Planning Domains (YG), pp. 87–95.

ICML-1994-GiordanaSZ #algorithm #concept #learning #search-based

Learning Disjunctive Concepts by Means of Genetic Algorithms (AG, LS, FZ), pp. 96–104.

ICML-1994-Heger #learning

Consideration of Risk in Reinformance Learning (MH), pp. 105–111.

ICML-1994-HsuK #optimisation #query #semantics

Rule Introduction for Semantic Query Optimization (CNH, CAK), pp. 112–120.

ICML-1994-JohnKP #problem #set

Irrelevant Features and the Subset Selection Problem (GHJ, RK, KP), pp. 121–129.

ICML-1994-KietzL #algorithm #induction #logic programming #performance

An Efficient Subsumption Algorithm for Inductive Logic Programming (JUK, ML), pp. 130–138.

ICML-1994-KoppelSF

Getting the Most from Flawed Theories (MK, AMS, RF), pp. 139–147.

ICML-1994-LewisC #learning #nondeterminism

Heterogenous Uncertainty Sampling for Supervised Learning (DDL, JC), pp. 148–156.

ICML-1994-Littman #framework #game studies #learning #markov #multi

Markov Games as a Framework for Multi-Agent Reinforcement Learning (MLL), pp. 157–163.

ICML-1994-Mahadevan #case study #learning

To Discount or Not to Discount in Reinforcement Learning: A Case Study Comparing R Learning and Q Learning (SM), pp. 164–172.

ICML-1994-MahoneyM

Comparing Methods for Refining Certainty-Factor Rule-Bases (JJM, RJM), pp. 173–180.

ICML-1994-Mataric #learning

Reward Functions for Accelerated Learning (MJM), pp. 181–189.

ICML-1994-MooreL #algorithm #fault #performance #validation

Efficient Algorithms for Minimizing Cross Validation Error (AWM, MSL), pp. 190–198.

ICML-1994-MurphyP

Revision of Production System Rule-Bases (PMM, MJP), pp. 199–207.

ICML-1994-OpitzS #knowledge-based #network #search-based #using

Using Genetic Search to Refine Knowledge-based Neural Networks (DWO, JWS), pp. 208–216.

ICML-1994-PazzaniMMAHB #classification

Reducing Misclassification Costs (MJP, CJM, PMM, KMA, TH, CB), pp. 217–225.

ICML-1994-PengW #incremental #multi

Incremental Multi-Step Q-Learning (JP, RJW), pp. 226–232.

ICML-1994-Quinlan #category theory

The Minimum Description Length Principle and Categorical Theories (JRQ), pp. 233–241.

ICML-1994-RachlinKSA #comprehension #reasoning #towards

Towards a Better Understanding of Memory-based Reasoning Systems (JR, SK, SS, DWA), pp. 242–250.

ICML-1994-RoscaB #programming #search-based #self

Hierarchical Self-Organization in Genetic programming (JPR, DHB), pp. 251–258.

ICML-1994-Schaffer #performance

A Conservation Law for Generalization Performance (CS), pp. 259–265.

ICML-1994-SchapireW #algorithm #analysis #learning #on the #worst-case

On the Worst-Case Analysis of Temporal-Difference Learning Algorithms (RES, MKW), pp. 266–274.

ICML-1994-Sebag #algorithm #constraints #induction

A Constraint-based Induction Algorithm in FOL (MS), pp. 275–283.

ICML-1994-SinghJJ #learning #markov #process

Learning Without State-Estimation in Partially Observable Markovian Decision Processes (SPS, TSJ, MIJ), pp. 284–292.

ICML-1994-Skalak #algorithm #feature model #prototype #random

Prototype and Feature Selection by Sampling and Random Mutation Hill Climbing Algorithms (DBS), pp. 293–301.

ICML-1994-TchoumatchenkoG #framework #learning

A Baysian Framework to Integrate Symbolic and Neural Learning (IT, JGG), pp. 302–308.

ICML-1994-ThamP #architecture #composition

A Modular Q-Learning Architecture for Manipulator Task Decomposition (CKT, RWP), pp. 309–317.

ICML-1994-Utgoff #algorithm #incremental #induction

An Improved Algorithm for Incremental Induction of Decision Trees (PEU), pp. 318–325.

ICML-1994-Valdes-PerezP #behaviour #heuristic

A Powerful Heuristic for the Discovery of Complex Patterned Behaviour (REVP, AP), pp. 326–334.

ICML-1994-WeissI

Small Sample Decision tree Pruning (SMW, NI), pp. 335–342.

ICML-1994-ZelleMK #bottom-up #induction #logic programming #top-down

Combining Top-down and Bottom-up Techniques in Inductive Logic Programming (JMZ, RJM, JBK), pp. 343–351.

ICML-1994-ZuckerG #concept #learning

Selective Reformulation of Examples in Concept Learning (JDZ, JGG), pp. 352–360.

ICML-1994-Jordan #approach #modelling #statistics

A Statistical Approach to Decision Tree Modeling (MIJ), pp. 363–370.

ICML-1994-Muggleton #induction #logic programming

Bayesian Inductive Logic Programming (SM), pp. 371–379.

ICML-1994-Pereira #bias #machine learning #natural language #problem

Frequencies vs. Biases: Machine Learning Problems in Natural Language Processing — Abstract (FCNP), p. 380.