Results 1  10
of
67
Learning Stochastic Logic Programs
, 2000
"... Stochastic Logic Programs (SLPs) have been shown to be a generalisation of Hidden Markov Models (HMMs), stochastic contextfree 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 firstorder range ..."
Abstract

Cited by 1057 (71 self)
 Add to MetaCart
Stochastic Logic Programs (SLPs) have been shown to be a generalisation of Hidden Markov Models (HMMs), stochastic contextfree 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 firstorder rangerestricted 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 nearmaximal 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 userdefined 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.
Inverse entailment and Progol
, 1995
"... This paper firstly provides a reappraisal of the development of techniques for inverting deduction, secondly introduces ModeDirected Inverse Entailment (MDIE) as a generalisation and enhancement of previous approaches and thirdly describes an implementation of MDIE in the Progol system. Progol ..."
Abstract

Cited by 631 (59 self)
 Add to MetaCart
This paper firstly provides a reappraisal of the development of techniques for inverting deduction, secondly introduces ModeDirected Inverse Entailment (MDIE) as a generalisation and enhancement of previous approaches and thirdly describes an implementation of MDIE in the Progol system. Progol is implemented in C and available by anonymous ftp. The reassessment of previous techniques in terms of inverse entailment leads to new results for learning from positive data and inverting implication between pairs of clauses.
Automated Refinement of FirstOrder HornClause Domain Theories
 MACHINE LEARNING
, 1995
"... Knowledge acquisition is a difficult, errorprone, and timeconsuming task. The task of automatically improving an existing knowledge base using learning methods is addressed by the class of systems performing theory refinement. This paper presents a system, Forte (FirstOrder Revision of Theories f ..."
Abstract

Cited by 81 (7 self)
 Add to MetaCart
Knowledge acquisition is a difficult, errorprone, and timeconsuming task. The task of automatically improving an existing knowledge base using learning methods is addressed by the class of systems performing theory refinement. This paper presents a system, Forte (FirstOrder Revision of Theories from Examples), which refines firstorder Hornclause theories by integrating a variety of different revision techniques into a coherent whole. Forte uses these techniques within a hillclimbing framework, guided by a global heuristic. It identifies possible errors in the theory and calls on a library of operators to develop possible revisions. The best revision is implemented, and the process repeats until no further revisions are possible. Operators are drawn from a variety of sources, including propositional theory refinement, firstorder induction, and inverse resolution. Forte is demonstrated in several domains, including logic programming and qualitative modelling.
Nonmonotonic Learning
 Inductive Logic Programming
, 1992
"... This paper addresses methods of specialising firstorder theories within the context of incremental learning systems. We demonstrate the shortcomings of existing firstorder incremental learning systems with regard to their specialisation mechanisms. We prove that these shortcomings are fundamental ..."
Abstract

Cited by 58 (11 self)
 Add to MetaCart
This paper addresses methods of specialising firstorder theories within the context of incremental learning systems. We demonstrate the shortcomings of existing firstorder incremental learning systems with regard to their specialisation mechanisms. We prove that these shortcomings are fundamental to the use of classical logic. In particular, minimal "correcting " specialisations are not always obtainable within this framework. We propose instead the adoption of a specialisation scheme based on an existing nonmonotonic logic formalism. This approach overcomes the problems that arise with incremental learning systems which employ classical logic. As a sideeffect of the formal proofs developed for this paper we define a function called "deriv" which turns out to be an improvement on an existing explanationbasedgeneralisation (EBG) algorithm. Prolog code and a description of the relationship between "deriv" and the previous EBG algorithm are described in an appendix. 1 Introduction ...
Inductive Synthesis of Recursive Logic Programs
, 1997
"... The inductive synthesis of recursive logic programs from incomplete information, such as input/output examples, is a challenging subfield both of ILP (Inductive Logic Programming) and of the synthesis (in general) of logic programs from formal specifications. We first overview past and present achie ..."
Abstract

Cited by 34 (8 self)
 Add to MetaCart
The inductive synthesis of recursive logic programs from incomplete information, such as input/output examples, is a challenging subfield both of ILP (Inductive Logic Programming) and of the synthesis (in general) of logic programs from formal specifications. We first overview past and present achievements, focusing on the techniques that were designed specifically for the inductive synthesis of recursive logic programs, but also discussing a few general ILP techniques that can also induce nonrecursive hypotheses. Then we analyse the prospects of these techniques in this task, investigating their applicability to software engineering as well as to knowledge acquisition and discovery.
Learning Concepts from Sensor Data of a Mobile Robot
 Machine Learning
, 1996
"... . Machine learning can be a most valuable tool for improvingthe flexibility and efficiency of robot applications. Many approaches to applying machine learning to robotics are known. Some approaches enhance the robot's highlevel processing, the planning capabilities. Other approaches enhance the low ..."
Abstract

Cited by 32 (6 self)
 Add to MetaCart
. Machine learning can be a most valuable tool for improvingthe flexibility and efficiency of robot applications. Many approaches to applying machine learning to robotics are known. Some approaches enhance the robot's highlevel processing, the planning capabilities. Other approaches enhance the lowlevel processing, the control of basic actions. In contrast, the approach presented in this paper uses machine learning for enhancing the link between the lowlevel representations of sensing and action and the highlevel representation of planning. The aim is to facilitate the communication between the robot and the human user. A hierarchy of concepts is learned from route records of a mobile robot. Perception and action are combined at every level, i.e., the concepts are perceptually anchored. The relational learning algorithm grdt has been developed which completely searches in a hypothesis space, that is restricted by rule schemata, which the user defines in terms of grammars. Keywords...
Inductive Logic Programming: derivations, successes and shortcomings
 SIGART Bulletin
, 1993
"... Inductive Logic Programming (ILP) is a research area which investigates the construction of firstorder definite clause theories from examples and background knowledge. ILP systems have been applied successfully in a number of realworld domains. These include the learning of structureactivity rules ..."
Abstract

Cited by 31 (3 self)
 Add to MetaCart
Inductive Logic Programming (ILP) is a research area which investigates the construction of firstorder definite clause theories from examples and background knowledge. ILP systems have been applied successfully in a number of realworld domains. These include the learning of structureactivity rules for drug design, finiteelement mesh design rules, rules for primarysecondary prediction of protein structure and fault diagnosis rules for satellites. There is a well established tradition of learninginthelimit results in ILP. Recently some results within Valiant's PAClearning 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 generalpurpose, efficient approach to predicate invention is demonstrated. ILP is underconstrained by its logical ...
An Efficient Subsumption Algorithm for Inductive Logic Programming
 IN PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING
, 1994
"... In this paper we investigate the efficiency of ` subsumption (` ` ), the basic provability relation in ILP. As D ` ` C is NPcomplete even if we restrict ourselves to linked Horn clauses and fix C to contain only a small constant number of literals, we investigate in several restrictions of D. ..."
Abstract

Cited by 31 (3 self)
 Add to MetaCart
In this paper we investigate the efficiency of ` subsumption (` ` ), the basic provability relation in ILP. As D ` ` C is NPcomplete even if we restrict ourselves to linked Horn clauses and fix C to contain only a small constant number of literals, we investigate in several restrictions of D. We first adapt the notion of determinate clauses used in ILP and show that `subsumption is decidable in polynomial time if D is determinate with respect to C. Secondly, we adapt the notion of klocal Horn clauses and show that ` subsumption is efficiently computable for some reasonably small k. We then show how these results can be combined, to give an efficient reasoning procedure for determinate klocal Horn clauses, an ILPproblem recently suggested to be polynomial predictable by Cohen (1993) by a simple counting argument. We finally outline how the `reduction algorithm, an essential part of every lgg ILPlearning algorithm, can be improved by these ideas.
SpecifictoGeneral Learning for Temporal Events with Application to Learning . . .
 JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH
, 2002
"... We develop, analyze, and evaluate a novel, supervised, specifictogeneral learner for a simple temporal logic and use the resulting algorithm to learn visual event definitions from video sequences. First, we introduce a simple, propositional, temporal, eventdescription language called AMA that ..."
Abstract

Cited by 30 (3 self)
 Add to MetaCart
We develop, analyze, and evaluate a novel, supervised, specifictogeneral learner for a simple temporal logic and use the resulting algorithm to learn visual event definitions from video sequences. First, we introduce a simple, propositional, temporal, eventdescription language called AMA that is sufficiently expressive to represent many events yet sufficiently restrictive to support learning. We then give algorithms, along with lower and upper complexity bounds, for the subsumption and generalization problems for AMA formulas. We present a positiveexamples  only specifictogeneral learning method based on these algorithms. We also present a polynomialtime  computable "syntactic" subsumption test that implies semantic subsumption without being equivalent to it. A generalization algorithm based on syntactic subsumption can be used in place of semantic generalization to improve the asymptotic complexity of the resulting learning algorithm. Finally
Inverting Implication
 Artificial Intelligence Journal
, 1992
"... All generalisations within logic involve inverting implication. Yet, ever since Plotkin's work in the early 1970's methods of generalising firstorder clauses have involved inverting the clausal subsumption relationship. However, even Plotkin realised that this approach was incomplete. Since inversi ..."
Abstract

Cited by 26 (2 self)
 Add to MetaCart
All generalisations within logic involve inverting implication. Yet, ever since Plotkin's work in the early 1970's methods of generalising firstorder clauses have involved inverting the clausal subsumption relationship. However, even Plotkin realised that this approach was incomplete. Since inversion of subsumption is central to many Inductive Logic Programming approaches, this form of incompleteness has been propagated to techniques such as Inverse Resolution and Relative Least General Generalisation. A more complete approach to inverting implication has been attempted with some success recently by Lapointe and Matwin. In the present paper the author derives general solutions to this problem from first principles. It is shown that clausal subsumption is only incomplete for selfrecursive clauses. Avoiding this incompleteness involves algorithms which find "nth roots" of clauses. Completeness and correctness results are proved for a nondeterministic algorithms which constructs nth ro...