21.
Bayesian Inductive Logic Programming
- Stephen Muggleton
Inductive Logic Programming (ILP) involves the
construction of first-order definite clause theories
from examples and background knowledge. Unlike
both traditional Machine Learning and Computational
Learning Theory, ILP is based on lockstep
development of Theory, Implementations and
Applications. ILP systems have successful applications
in the learning of structure-activity rules
for drug design, semantic grammars rules, finite
element mesh design rules and rules for prediction
of protein structure and mutagenic molecules. The
strong applications in ILP can be contrasted with
relatively weak PAC-learning results (even highlyrestricted
forms of logic programs are known to be
prediction-hard). It has been recently argued that
the mismatch is due to distributional assumptions
made in application domains. These assumptions
can be modelled as a...
22.
Anytime Inductive Logic Programming
- Tony Lindgren
Anytime algorithms refers to algorithms that always
" can produce a result. Often the result of the
algorithm depends on the time at hand, the longer
the time, the better the answer. In this paper we
present an easy way of turning regular Inductive Logic
Programming (ILP) algorithms such as Divide-AndConquer
(DAC) and Separate-And-Conquer (SAC)
into anytime algorithms. We conduct experiments
with these anytime algorithms and introduce a simple
heuristic called squared quota, that we compare
with an established one, information gain. It seems
that squared quota is better suited for a small window
size of example data, and hence better to use in anytime
systems. A comparison between SAC and DAC
reveals that...
23.
A Perspective on Inductive Logic Programming
- Luc De Raedt
. The state-of-the-art in inductive logic programming is surveyed by
analyzing the approach taken by this field over the past 8 years. The analysis
investigates the roles of 1) logic programming and machine learning, of 2) theory,
techniques and applications, of 3) various technical problems addressed
within inductive logic programming.
1 Introduction
The term inductive logic programming was first coined by Stephen Muggleton in
1990 [1]. Inductive logic programming is concerned with the study of inductive machine
learning within the representations offered by computational logic. Since 1991,
annual international workshops have been organized [2-8]. This paper is an attempt to
analyze the developments within this field. Particular attention is devoted...
24.
Towards Practical Inductive Logic Programming
- Luc De Raedt
Despite significant technical advances within the field of inductive logic programming, it is still the case that inductive logic programming engines are impractical in the sense that they are hard to use for the non-expert. Often phrased critiques include: it is unclear 1) when to use inductive logic programming, 2) how to formulate the learning task and to set the necessary parameters (such as bias, background knowledge and perhaps control parameters), and 3) which inductive logic programming system to use. Furthermore, the use of Prolog as the representation language often forms an additional barrier for the typical end-user of data...
25.
Towards Practical Inductive Logic Programming
- Luc De Raedt
Current inductive logic programming engines are not practical in the sense that they are hard to use and understand by the naive end-user. Various guidelines are presented for developing practical inductive logic programming engines that should be widely applicable and easy to use by the typical end-user of data mining systems. The presented guidelines summarize the author's personal experiences and opinions gathered during the design and development of various inductive logic programming systems. In forming these opinions, the author was strongly influenced by discussions within the consortium of the ESPRIT project Aladin, though the guidelines do not necessarily reflect any...
26.
Inductive Logic Programming for Nuclear Power Plants Monitoring
- Claire Nicolini; Cea Centre De Valduc; François JACQUENET; Marc Bernard
Nuclear power plants monitoring is a very tricky task because there is no formal model of the plants when a malfunction occurs. The experts of a plant have some knowledge on the management of the plant but it is very difficult for us to explain what may happen in such or such configuration of the plant. In this paper, we use a new learning technique to model the malfunction of a nuclear plant. We use Inductive Logic Programming to induce some logic programs that model the usual malfunctions of the plant and may be used later to diagnose and correct...
27.
Pharmacophore Discovery using the Inductive Logic Programming System Progol
- Paul Finn; David Page; Ron Kohavi; Foster Provost
. This paper presents a case study of a machine-aided knowledge discovery process within the general area of drug design. Within drug design, the particular problem of pharmacophore discovery is isolated, and the Inductive Logic Programming (ILP) system progol is applied to the problem of identifying potential pharmacophores for ACE inhibition. The case study reported in this paper supports four general lessons for machine learning and knowledge discovery, as well as more specific lessons for pharmacophore discovery, for Inductive Logic Programming, and for ACE inhibition. The general lessons for machine learning and knowledge discovery are as follows. 1. An initial...
28.
Probabilistic Inductive Logic Programming
- Luc De Raedt,Kristian Kersting
Probabilistic inductive logic programming, sometimes also
called statistical relational learning, addresses one of the central questions
of artificial intelligence: the integration of probabilistic reasoning
with first order logic representations and machine learning. A rich variety
of di#erent formalisms and learning techniques have been developed. In
the present paper, we start from inductive logic programming and sketch
how it can be extended with probabilistic methods.
29.
AILP: Abductive Inductive Logic Programming
- Marc Denecker
Inductive Logic Programming (ILP) is often
situated as a research area emerging at the intersection
of Machine Learning and Logic Programming
(LP). This paper makes the link
more clear between ILP and LP, in particular,
between ILP and Abductive Logic Programming
(ALP), i.e., LP extended with abductive
reasoning. We formulate a generic framework
for handling incomplete knowledge. This
framework can be instantiated both to ALP
and ILP approaches. By doing so more light
is shed on the relationship between abduction
and induction. As an example we consider the
abductive procedure SLDNFA, and modify it
into an inductive procedure which we call SLDNFAI.
Keywords: Inductive Logic Programming, Abductive
Logic Programming, Incomplete Knowledge, Intensional
Knowledge Base Updating, Theory Revision.
1...
30.
Extending Classical Logic with Inductive Definitions
- Marc Denecker
The goal of this paper is to extend classical logic with a generalized notion of inductive definition supporting positive and negative induction, to investigate the properties of this logic, its relationships to other logics in the area of non-monotonic reasoning, logic programming and deductive databases, and to show its application for knowledge representation by giving a typology of definitional knowledge.
31.
Extending Classical Logic with Inductive Definitions
- Marc Denecker
The goal of this paper is to extend classical logic with
a generalized notion of inductive definition supporting
positive and negative induction, to investigate the
properties of this logic, its relationships to other logics
in the area of non-monotonic reasoning, logic programming
and deductive databases, and to show its application
for knowledge representation by giving a typology
of definitional knowledge.
32.
Extending Classical Logic with Inductive De nitions
- De Nitions,Marc Denecker
The goal of this paper is to extend classical logic with a generalized notion of inductive definition supporting positive and negative induction, to investigate the properties of this logic, its relationships to other logics in the area of non-monotonic reasoning, logic programming and deductive databases, and to show its application for knowledge representation by giving a typology of definitional knowledge.
33.
Parallel Inductive Logic Programming
- Luc Dehaspe,Luc De Raedt
The generic task of Inductive Logic Programming (ILP) is to search a predefined
subspace of first-order logic for hypotheses that in some respect explain examples and
background knowledge. In this paper we consider the development of parallel implementations
of ILP systems. A first part discusses the division of the ILP-task into
subtasks that can be handled concurrently by multiple processes executing a common
sequential ILP algorithm. We define the notion of a valid partition of an ILP-task, and
test this definition against two problem specifications that have been employed within
ILP. The second part of the paper focuses on the algorithmic description, prototypical
implementation, and comparative evaluation of...
34.
Parallel Inductive Logic Programming
- Luc Dehaspe,Luc De Raedt
The generic task of Inductive Logic Programming (ILP) is to search a predefined
subspace of first-order logic for hypotheses that in some respect explain examples and
background knowledge. In this paper we consider the development of parallel implementations
of ILP systems. A first part discusses the division of the ILP-task into
subtasks that can be handled concurrently by multiple processes executing a common
sequential ILP algorithm. We define the notion of a valid partition of an ILP-task,
and test this definition against two problem specifications that have been employed
within ILP. The second part of the paper focuses on the comparative evaluation of a
parallel version of the...
35.
Parallel Inductive Logic Programming
- Luc Dehaspe,Luc De Raedt
The generic task of Inductive Logic Programming (ILP) is to search a predefined
subspace of first-order logic for hypotheses that in some respect explain examples and
background knowledge. In this paper we consider the development of parallel implementations
of ILP systems. A first part discusses the division of the ILP-task into
subtasks that can be handled concurrently by multiple processes executing a common
sequential ILP algorithm. We define the notion of a valid partition of an ILP-task,
and test this definition against two problem specifications that have been employed
within ILP. The second part of the paper focuses on the comparative evaluation of a
parallel version of the...
36.
Parallel Inductive Logic Programming
- Luc Dehaspe,Luc De Raedt
The generic task of Inductive Logic Programming (ILP) is to search
a predefined subspace of first-order logic for hypotheses that in some
respect explain examples and background knowledge. In this paper we
consider the development of parallel implementations of ILP systems.
A first part discusses the division of the ILP-task into subtasks that
can be handled concurrently by multiple processes executing a common
sequential ILP algorithm. We define the notion of a valid partition of
an ILP-task, and test this definition against two problem specifications
that have been employed within ILP. The second part of the paper focuses
on the algorithmic description, prototypical implementation, and
comparative evaluation of a parallel...
37.
Developments in Inductive Logic Programming
- Stephen Muggleton
Inductive Logic Programming (ILP) is a research area formed at the intersection of Machine Learning
and Logic Programming. ILP systems develop predicate descriptions from examples and background
knowledge. The examples, background knowledge and nal descriptions are all described as logic programs.
A unifying theory of Inductive Logic Programming is being built up around lattice-based concepts
such as renement, least general generalisation, inverse resolution and most specic corrections. In addition
to a well established tradition of learning-in-the-limit results, recently some results within Valiant's
PAC-learning framework have been demonstrated for ILP systems. Presently successful applications
areas for ILP systems include the learning of structure-activity rules for drug design, nite-element...
38.
Application of Inductive Logic Programming for Learning ECG Waveforms
- Gabriella Kokai; Zolt'an Alexin; Tibor Gyim'othy
. In this paper a learning system is presented which integrates an ECG waveform classifier (called PECG) with an interactive learner (called IMPUT). The PECG system is based on an attribute grammar specification of ECGs that has been transformed to Prolog. The IMPUT system combines the interactive debugging technique IDT with the unfolding algorithm introduced in SPECTRE. Using the IMPUT system we can effectively assist in preparing the correct description of the basic structures of ECG waveforms. 4 Keywords: inductive logic programming, program specialization, syntactic pattern recognition 1 Introduction In this paper a complex system is presented that is able...
39.
Pharmacophore Discovery using the Inductive Logic Programming System Progol
- Paul Finn; David Page; Ronny Kohavi; Foster Provost
. This paper is a case study of a machine aided knowledge discovery process within the general area of drug design. More specifically, the paper describes a sequence of experiments in which an Inductive Logic Programming(ILP) system is used for pharmacophore discovery. Within drug design, a pharmacophore is a description of the substructure of a ligand (a small molecule) which is responsible for medicinal activity. This medicinal activity is produced by interaction between the ligand and a binding site on a target protein. ILP was chosen by the domain expert (first author) at Pfizer since active molecules are most naturally...
40.
Application of Inductive Logic Programming for Learning ECG Waveforms
- Gabriella Kokai; Zoltán Alexin; Tibor Gyimóthy
. In this paper a learning system is presented which integrates an ECG waveform classifier (called PECG) with an interactive learner (called IMPUT). The PECG system is based on an attribute grammar specification of ECGs that has been transformed to Prolog. The IMPUT system combines the interactive debugging technique IDT with the unfolding algorithm introduced in SPECTRE. Using the IMPUT system we can effectively assist in preparing the correct description of the basic structures of ECG waveforms. The application of the system for learning ECG waveforms is demonstrated with the help of an example. 4 Keywords: inductive logic programming, program...
