Due to the inadequacy of attribute-only representations for many learning problems, there is now a renewed interest in algorithms employing first-order logic or restricted variants thereof as their knowledge representation. In this paper, we give a brief overview of the dimensions along which the complexity of learning in such representations can be controlled. We then present RDT, a model-based learning algorithm for function-free Horn clauses with negation that introduces two new means of complexity control, namely the use of syntactic rule models, and the use of a task-oriented domain topology. We briefly describe some preliminary application results of RDT within the knowledge acquisition system MOBAL, and present directions of further research.

Abstract. The available concept-learners only partially fulfill the needs imposed by the learning apprentice generation of learners. We present a novel approach to interactive concept-learning and constructive induction that better fits the requirements imposed by the learning apprentice paradigm. The approach is incorporated in the system Clint-Cia, which integrates several user-friendly features into one working whole: it is interactive, generates examples, shifts its bias, identifies concepts in the limit, copes with indirect relevance, recovers from errors, performs constructive induction and invents new concepts by analogy to previously learned ones.

Abstract not found

We discuss the adoption of a three-valued setting for inductive concept learning. Distinguishing between what is true, what is false and what is unknown can be useful in situations where decisions have tobetaken on the basis of scarce, ambiguous, or downright contradictory information. In a three-valued setting, we learn a de nition for both the target concept and its opposite, considering positive and negative examples as instances of two disjoint classes. To this purpose, we adopt Extended Logic Programs (ELP) under a Well-Founded Semantics with explicit negation (WFSX) as the representation formalism for learning, and show how ELPs can be used to specify combinations of strategies in a declarative way also coping with contradiction and exceptions. Explicit negation is used to represent the opposite concept, while default negation is used to ensure consistency and to handle exceptions to general rules. Exceptions are represented by examples covered by the de nition for a concept that belong to the training set for the opposite concept. Standard Inductive Logic Programming techniques are employed to learn the concept and its opposite. Depending on the adopted technique, we can learn the most general or the least general

This paper presents an approach to domain modeling and knowledge acquisition that consists of a gradual and goal-driven improvement of an incomplete domain model provided by a human expen. Our approach is based on a multistrategy learning method that allows a system with incomplete knowledge to learn general inference or problem solving rules from specific facts or problem solving episodes received from the human expen. The system will learn the general knowledge pieces by considering all their possible instances in the current domain model. trying to learn complete and consistent descriptions. Because of the incompleteness of the domain model the learned rules will have exceptions that are eliminated by refining the definitions of the existing concepts or by defining new concepts.

. In the last decade, many efforts have been devoted to the exploration of techniques for learning and refining first order theories, as the necessary step for applying machine learning methodologies to real world applications. In this paper, we present a new approach to the integration of inductive and deductive learning techniques that seems to overcome some of the limitations of existing learning systems without imposing strong constraints or biases on both the representation language and the search space. In particular, a new search structure that enables the system to learn a structured knowledge base is proposed. Moreover, the learning system described in the paper can be used both to learn new knowledge from scratch and to refine an existing background theory. 1. Introduction Studies in learning first order logic representations has followed two main trends: on one hand, many efforts have been devoted to build learning systems that are able to synthesize logic programs [5, 6, 16...

In this paper, we investigate the integration of knowledge acquisition and machine learning techniques. We argue that existing machine learning techniques can be made more useful as knowledge acquisition tools by allowing the expert to have greater control over and interaction with the learning process. We describe a number of extensions to FOCL (a multistrategy Horn-clause learning program) that have greatly enhanced its power as a knowledge acquisition tool, paying particular attention to the utility of maintaining a connection between a rule and the set of examples explained by the rule. The objective of this research is to make the modification of a domain theory analogous to the use of a spread sheet. A prototype knowledge acquisition tool, FOCL-1-2-3, has been constructed in order to evaluate the strengths and weaknesses of this approach. 1 1.0 Introduction The emphasis of our research has been on the integration of machine learning and knowledge acquisition techniques to fac...

The symbolic approach to machine learning has developed algorithms for learning First Order Logic concept definitions. Nevertheless, most of them are limited because of their impossibility to cope with numeric features, typical of real-world data. In this paper, a method to face this problem is proposed. In particular, an extended version of the system ML-SMART is described, which is capable to automatically adjust the values of fuzzy sets used to define the semantics of the predicates in the concept description language. The learning strategy works in two separate phases: in the first one, the structure of the concept definition is learned by choosing tentative values for the fuzzy sets; in the second phase, the values are refined using a simple genetic algorithm, trying to get closer to an optimum assignment. The system is evaluated on a complex artificial domain, that shows the good potentialities of this approach. I. INTRODUCTION In the recent literature, inducing descriptions of s...

Inducing concept descriptions in First Order Logic is inherently a complex task. There are two main reasons: on one hand, the task is usually formulated as a search problem inside a very large space of logical descriptions which needs strong heuristics to be kept to manageable size. On the other hand, most developed algorithms are unable to handle numerical features, typically occurring in realworld data. In this paper, we describe the learning system SMART+, that embeds sophisticated knowledge-based heuristics to control the search process and is able to deal with numerical features. SMART+ can use different learning strategies, such as inductive, deductive and abductive ones, and exploits both backgruond knowledge and statistical evaluation criteria. Furthermore, it can use simple Genetic Algorithms to refine predicate semantics and this aspect will be described in detail. Finally, an evaluation of SMART+ performances is made on a complex task. 1 Introduction In the recent literature...

Contents Acknowledgments iii 1 Introduction 1 1.1 Limits of ILP . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.2 Proposed Solutions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.3 Structure of the Thesis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2 An Overview of Machine Learning 7 2.1 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.1.1 Learning Strategies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.1.2 Research Paradigm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.2 Inductive Concept Learning from Examples . . . . . . . . . . . . . . . . . . . 10 2.3 Representation Languages in Inductive Reasoning . . . . . . . . . . . . . . . . 12 3 Inductive Logic Programming 17 3.1 Logic Programming Preliminaries . . . . . . . . . . . . . . . . . . . . . . . . . 17 3.2 Learning from Entailment . . . . . . . . . . . . . . . . . . . . . . . . . . . . .