The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
AI systems must be able to learn, reason logically, and handle uncertainty. While much research has focused on each of these goals individually, only recently have we begun to attempt to achieve all three at once. In this talk I will describe Markov logic, a representation that combines the full power of first-order logic and probabilistic graphical models, and algorithms for learning and inference...
Program synthesis is the systematic, usually automatic construction of correct and efficient executable code from declarative statements. Program synthesis is routinely used in industry to generate GUIs and for database support.
Inductive logic programming can be viewed as a style of statistical inference where the model that is inferred to explain the observed data happens to be a logic program. In general, logic programs have important differences to other models (such as linear models, tree-based models, etc) found in the statistical literature. This why we have ILP conferences!
PharmaDM was founded end 2000 as a spin-off from three European universities (Oxford, Aberystwyth, and Leuven) that participated in two subsequent EC projects on Inductive Logic Programming (ILP I-II, 1992-1998). Amongst the projects highlights was a series of publications that demonstrated the added-value of ILP in applications related to the drug discovery process. The mission of PharmaDM is to...
The generation and testing of hypotheses is widely considered to be the primary method by which Science progresses. So much so, that it is still common to find a scientific proposal or an intellectual argument damned on the grounds that “it has no hypothesis being tested”, “it is merely a fishing expedition”, and so on. Extreme versions run “if there is no hypothesis, it is not Science”, the clear...
We have been applying Inductive Logic Programming (ILP) to the task of learning how to extract relations from biomedical text (specifically, Medline abstracts). Our primary focus has been learning to recognize instances of “this protein is localized in this part of the cell” from labeled training examples. ILP allows one to naturally make use of substantial background knowledge (e. g., biomedical...
For the last ten years a lot of work has been devoted to propositionalization techniques in relational learning. These techniques change the representation of relational problems to attribute-value problems in order to use well-known learning algorithms to solve them. Propositionalization approaches have been successively applied to various problems but are still considered as ad hoc techniques. In...
The LogAn-H system is a bottom up ILP system for learning multi-clause and multi-predicate function free Horn expressions in the framework of learning from interpretations. The paper introduces a new implementation of the same base algorithm which gives several orders of magnitude speedup as well as extending the capabilities of the system. New tools include several fast engines for subsumption tests,...
This paper focuses on inductive learning of recursive logical theories from a set of examples. This is a complex task where the learning of one predicate definition should be interleaved with the learning of the other ones in order to discover predicate dependencies. To overcome this problem we propose a variant of the separate-and-conquer strategy based on parallel learning of different predicate...
Multi-relational rule mining is important for knowledge discovery in relational databases as it allows for discovery of patterns involving multiple relational tables. Inductive logic programming (ILP) techniques have had considerable success on a variety of multi-relational rule mining tasks, however, most ILP systems do not scale to very large datasets. In this paper we present two extensions to...
One challenge faced by many Inductive Logic Programming (ILP) systems is poor scalability to problems with large search spaces and many examples. Randomized search methods such as stochastic clause selection (SCS) and rapid random restarts (RRR) have proven somewhat successful at addressing this weakness. However, on datasets where hypothesis evaluation is computationally expensive, even these algorithms...
Many domains in the field of Inductive Logic Programming (ILP) involve highly unbalanced data. Our research has focused on Information Extraction (IE), a task that typically involves many more negative examples than positive examples. IE is the process of finding facts in unstructured text, such as biomedical journals, and putting those facts in an organized system. In particular, we have focused...
Successful application of Machine Learning to certain real-world situations sometimes requires to take into account relations among objects. Inductive Logic Programming, being based on First-Order Logic as a representation language, provides a suitable learning framework to be adopted in these cases. However, the intrinsic complexity of this framework, added to the complexity of the specific application...
ILP systems induce first-order clausal theories performing a search through very large hypotheses spaces containing redundant hypotheses. The generation of redundant hypotheses may prevent the systems from finding good models and increases the time to induce them. In this paper we propose a classification of hypotheses redundancy and show how expert knowledge can be provided to an ILP system to avoid...
In this paper, we study the generalization algorithms for second-order terms, which are treated as first-order terms with function variables, under an instantiation order denoted by≽. First, we extend the least generalization algorithm lg for a pair of first-order terms under≽, introduced by Plotkin and Reynolds, to the one for a pair of second-order terms. The extended algorithm lg, however, is insufficient...
There are two types of formalization for induction in logic. In descriptive induction, induced hypotheses describe rules with respect to observations with all predicates minimized. In explanatory induction, on the other hand, hypotheses abductively account for observations without any minimization principle. Both inductive methods have strength and weakness, which are complementary to each other....
Recent developments in the area of relational reinforcement learning (RRL) have resulted in a number of new algorithms. A theory, however, that explains why RRL works, seems to be lacking. In this paper, we provide some initial results on a theory of RRL. To realize this, we introduce a novel representation formalism, called logical Markov decision programs (LOMDPs), that integrates Markov Decision...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.