Machine Learning: ECML-95: 8th European Conference on Machine Learning, Heraclion, Crete, Greece, April 25 - 27, 1995. Proceedings (Lecture Notes in Computer Science, 912)

"This volume constitutes the proceedings of the Eighth European Conference on Machine Learning ECML-95, held in Heraclion, Crete in April 1995. Besides four invited papers the volume presents revised versions of 14 long papers and 26 short papers selected from a total of 104 submissions. The papers address all current aspects in the area of machine learning; also logic programming, planning, reasoning, and algorithmic issues are touched upon."--PUBLISHER'S WEBSITE Reasoning and learning in probabilistic and possibilistic networks: An overview....Pages 1-16 Problem decomposition and the learning of skills....Pages 17-31 Machine learning in the world wide web....Pages 32-32 Abstract computer models: Towards a new method for theorizing about adaptive agents....Pages 33-52 Learning abstract planning cases....Pages 53-76 The role of prototypicality in exemplar-based learning....Pages 77-91 Specialization of recursive predicates....Pages 92-106 A distributed genetic algorithm improving the generalization behavior of neural networks....Pages 107-121 Learning non-monotonic logic programs: Learning exceptions....Pages 122-137 A comparative utility analysis of case-based reasoning and control-rule learning systems....Pages 138-150 A minimization approach to propositional inductive learning....Pages 151-160 On concept space and hypothesis space in case-based learning algorithms....Pages 161-173 The power of decision tables....Pages 174-189 Pruning multivariate decision trees by hyperplane merging....Pages 190-199 Multiple-Knowledge Representations in concept learning....Pages 200-217 The effect of numeric features on the scalability of inductive learning programs....Pages 218-231 Analogical logic program synthesis from examples....Pages 232-244 A guided tour through hypothesis spaces in ILP....Pages 245-259 JIGSAW: Puzzling together RUTH and SPECTRE (Extended abstract)....Pages 261-266 Discovery of constraints and data dependencies in relational databases (Extended abstract)....Pages 267-270 Learning disjunctive normal forms in a dual classifier system (Extended abstract)....Pages 271-274 The effects of noise on efficient incremental induction (Extended abstract)....Pages 275-278 Analysis of Rachmaninoff's piano performances using inductive logic programming (Extended abstract)....Pages 279-282 Handling real numbers in ILP: A step towards better behavioural clones (Extended abstract)....Pages 283-286 Simplifying decision trees by pruning and grafting: New results (Extended abstract)....Pages 287-290 A tight integration of pruning and learning (Extended abstract)....Pages 291-294 Decision-tree based neural network (Extended abstract)....Pages 295-298 Learning recursion with iterative bootstrap induction (Extended abstract)....Pages 299-302 Patching proofs for reuse (Extended abstract)....Pages 303-306 Adapting to drift in continuous domains (Extended abstract)....Pages 307-310 Parallel recombinative reinforcement learning (Extended abstract)....Pages 311-314 Learning to solve complex tasks for reactive systems (Extended abstract)....Pages 315-318 Co-operative Reinforcement Learning by payoff filters (Extended abstract)....Pages 319-322 Automatic synthesis of control programs by combination of learning and problem solving methods (Extended abstract)....Pages 323-326 Analytical learning guided by empirical technology: An approach to integration (Extended abstract)....Pages 327-330 A new MDL measure for robust rule induction (Extended abstract)....Pages 331-334 Class-driven statistical discretization of continuous attributes (Extended abstract)....Pages 335-338 Generating neural networks through the induction of threshold logic unit trees (Extended abstract)....Pages 339-342 Learning classification rules using lattices (Extended abstract)....Pages 343-346 Hybrid classification: Using axis-parallel and oblique subdivisions of the attribute space (Extended abstract)....Pages 347-350 An induction-based control for genetic algorithms (Extended abstract)....Pages 351-355 Fender: An approach to theory restructuring (extended abstract)....Pages 356-359 Language series revisited: The complexity of hypothesis spaces in ILP (Extended abstract)....Pages 360-363 Prototype, nearest neighbor and hybrid algorithms for time series classification (Extended abstract)....Pages 364-367

This volume constitutes the proceedings of the Eighth European Conference on Machine Learning ECML-95, held in Heraclion, Crete in April 1995.
Besides four invited papers the volume presents revised versions of 14 long papers and 26 short papers selected from a total of 104 submissions. The papers address all current aspects in the area of machine learning; also logic programming, planning, reasoning, and algorithmic issues are touched upon.

Due to its simplification of multivariate data analysis, graphical modelling is being increasingly recognized as an appropriate framework for both knowledge representation and inference under uncertainty [65].