Stochastic Logic Programs (SLPs) have been shown to be a generalisation of Hidden Markov Models (HMMs), stochastic context-free grammars, and directed Bayes' nets. A stochastic logic program consists of a set of labelled clauses p:C where p is in the interval [0,1] and C is a first-order range-restricted definite clause. This paper summarises the syntax, distributional semantics and proof techniques for SLPs and then discusses how a standard Inductive Logic Programming (ILP) system, Progol, has been modied to support learning of SLPs. The resulting system 1) nds an SLP with uniform probability labels on each definition and near-maximal Bayes posterior probability and then 2) alters the probability labels to further increase the posterior probability. Stage 1) is implemented within CProgol4.5, which differs from previous versions of Progol by allowing user-defined evaluation functions written in Prolog. It is shown that maximising the Bayesian posterior function involves nding SLPs with short derivations of the examples. Search pruning with the Bayesian evaluation function is carried out in the same way as in previous versions of CProgol. The system is demonstrated with worked examples involving the learning of probability distributions over sequences as well as the learning of simple forms of uncertain knowledge.

Abstract not found

Inductive Logic Programming (ILP) is a research area which investigates the construction of first-order definite clause theories from examples and background knowledge. ILP systems have been applied successfully in a number of real-world domains. These include the learning of structureactivity rules for drug design, finite-element mesh design rules, rules for primary-secondary prediction of protein structure and fault diagnosis rules for satellites. There is a well established tradition of learning-in-the-limit results in ILP. Recently some results within Valiant's PAC-learning framework have also been demonstrated for ILP systems. In this paper it is argued that algorithms can be directly derived from the formal specifications of ILP. This provides a common basis for Inverse Resolution, ExplanationBased Learning, Abduction and Relative Least General Generalisation. A new general-purpose, efficient approach to predicate invention is demonstrated. ILP is underconstrained by its logical ...

Duce 1 is a Machine Learning system which suggests high-level domain features to the user (or oracle on the basis of a set of example object descriptions. Six transformation operators are used to successively compress the given examples by generalisation and feature construction. In this paper Duce is illustrated by way of its construction of a simple animal taxonomy and a hierarchical parity checker. However, Duce's main achievement has been the restructuring of a substantial expert system for deciding whether positions within the chess endgame of King-and-Pawn-on-a7 v. Kingand -Rook (KPa7KR) are won-for-white or not. The new concepts suggested by Duce for the chess expert system hierarchy were found to be meaningful by the chess expert Ivan Bratko. An existing manually created KPa7KR solution, which was the basis of a recent PhD thesis [ 20 ] , is compared to the structure interactively created by Duce. A second major expert system application of Duce was made within a diagnostic ...

There is increasing interest within the Machine Learning community in systems which automatically reformulate their problem representation by defining and constructing new predicates. A previous paper discussed such a system, called CIGOL, and gave a derivation for the mechanism of inverting individual steps in first order resolution proofs. In this paper we describe an enhancement to CIGOL's learning strategy which strongly constrains the formation of new concepts and hypotheses. The new strategy is based on results from algorithmic information theory. Using these results it is possible to compute the probability that the simplifications produced by adopting new concepts or hypotheses are not based on chance regularities within the examples. This can be derived from the amount of information compression produced by replacing the examples with the hypothesised concepts. CIGOL's improved performance, based on an approximation of this strategy, is demonstrated by way of the automatic "di...