Gerson Zaverucha

The Connectionist Inductive Learning and Logic Programming System

This paper presents the Connectionist Inductive Learning and Logic Programming System (C-IL2P). C-IL2P is a new massively parallel computational model based on a feedforward Artificial Neural Network that integrates inductive learning from examples and background knowledge, with deductive learning from Logic Programming. Starting with the background knowledge represented by a propositional logic program, a translation algorithm is applied generating a neural network that can be trained with examples. The results obtained with this refined network can be explained by extracting a revised logic program from it. Moreover, the neural network computes the stable model of the logic program inserted in it as background knowledge, or learned with the examples, thus functioning as a parallel system for Logic Programming. We have successfully applied C-IL2P to two real-world problems of computational biology, specifically DNA sequence analyses. Comparisons with the results obtained by some of the main neural, symbolic, and hybrid inductive learning systems, using the same domain knowledge, show the effectiveness of C-IL2P.

A Distribution Design Methodology for Object DBMS

The design of distributed databases involves making decisions on the fragmentation and placement of data and programs across the sites of a computer network. The first phase of the distribution design in a top-down approach is the fragmentation phase, which clusters in fragments the information accessed simultaneously by applications. Most distribution design algorithms propose a horizontal or vertical class fragmentation. However, the user has no assistance in the choice between these techniques. In this work we present a detailed methodology for the design of distributed object databases that includes: (i) an analysis phase, to indicate the most adequate fragmentation technique to be applied in each class of the database schema; (ii) a horizontal class fragmentation algorithm, and (iii) a vertical class fragmentation algorithm. Basically, the analysis phase is responsible for driving the choice between the horizontal and the vertical partitioning techniques, or even the combination of both, in order to assist distribution designers in the fragmentation phase of object databases. Experiments using our methodology have resulted in fragmentation schemas offering a high degree of parallelism together with an important reduction of irrelevant data.

Object Oriented Design Expertise Reuse: An Approach Based on Heuristics, Design Patterns and Anti-patterns

Object Oriented (OO) languages do not guarantee that a system is flexible enough to absorb future requirements, nor that its components can be reused in other contexts. This paper presents an approach to OO design expertise reuse, which is able to detect certain constructions that compromise future expansion or modification of OO systems, and suggest their replacement by more adequate ones. Both reengineering legacy systems, and systems that are still under development are considered by the approach. A tool (OOPDTool) was developed to support the approach, comprising a knowledge base of good design constructions, that correspond to heuristics and design patterns, as well as problematic constructions (i.e., anti-patterns).

Improving model construction of profile HMMs for remote homology detection through structural alignment

BackgroundRemote homology detection is a challenging problem in Bioinformatics. Arguably, profile Hidden Markov Models (pHMMs) are one of the most successful approaches in addressing this important problem. pHMM packages present a relatively small computational cost, and perform particularly well at recognizing remote homologies. This raises the question of whether structural alignments could impact the performance of pHMMs trained from proteins in the Twilight Zone, as structural alignments are often more accurate than sequence alignments at identifying motifs and functional residues. Next, we assess the impact of using structural alignments in pHMM performance.ResultsWe used the SCOP database to perform our experiments. Structural alignments were obtained using the 3DCOFFEE and MAMMOTH-mult tools; sequence alignments were obtained using CLUSTALW, TCOFFEE, MAFFT and PROBCONS. We performed leave-one-family-out cross-validation over super-families. Performance was evaluated through ROC curves and paired two tailed t-test.ConclusionWe observed that pHMMs derived from structural alignments performed significantly better than pHMMs derived from sequence alignment in low-identity regions, mainly below 20%. We believe this is because structural alignment tools are better at focusing on the important patterns that are more often conserved through evolution, resulting in higher quality pHMMs. On the other hand, sensitivity of these tools is still quite low for these low-identity regions. Our results suggest a number of possible directions for improvements in this area.

Artificial neural networks for power systems diagnosis

In this paper, we study the application of artificial neural networks to help a power systems operator to diagnose the faults during a disturbance. Towards this goal, an analysis of the training and simulation of an intelligent alarm processor of a simplified power system generation plant is presented in detail. This system is capable of diagnosing not only single faults but also multiple ones, even when the associated alarm set is incomplete. The results obtained demonstrate that neural network is a very powerful and reliable method for the solution of existing problems in power systems.<<ETX>>

Learning Logic Programs with Neural Networks

First-order theory refinement using neural networks is still an open problem. Towards a solution to this problem, we use inductive logic programming techniques to introduce FOCA, a First-Order extension of the Cascade ARTMAP system. To present such a first-order extension of Cascade ARTMAP, we: a) modify the network structure to handle first-order objects; b) define first-order versions of the main functions that guide all Cascade ARTMAP dynamics, the choice and match functions; c) define a first-order version of the propositional learning algorithm to approximate Plotkins least general generalization. Preliminary results indicate that our initial goal of learning logic programs using neural networks can be achieved.

Using the bottom clause and mode declarations in FOL theory revision from examples

Theory revision systems are designed to improve the accuracy of an initial theory, producing more accurate and comprehensible theories than purely inductive methods. Such systems search for points where examples are misclassified and modify them using revision operators. This includes trying to add antecedents to clauses usually following a top-down approach, considering all the literals of the knowledge base. Such an approach leads to a huge search space which dominates the cost of the revision process. ILP Mode Directed Inverse Entailment systems restrict the search for antecedents to the literals of the bottom clause. In this work the bottom clause and mode declarations are introduced in a first-order logic theory revision system aiming to improve the efficiency of the antecedent addition operation and, consequently, also of the whole revision process. Experimental results compared to revision system FORTE show that the revision process is on average 55 times faster, generating more comprehensible theories and still not significantly decreasing the accuracies obtained by the original revision process. Moreover, the results show that when the initial theory is approximately correct, it is more efficient to revise it than learn from scratch, obtaining significantly better accuracies. They also show that using the proposed theory revision system to induce theories from scratch is faster and generates more compact theories than when the theory is induced using a traditional ILP system, obtaining competitive accuracies.

Normal Programs and Multiple Predicate Learning

We study the problem of inducing normal programs of multiple predicates in the empirical ILP setting. We identify a class of normal logic programs that can be handled and induced in a top-down manner by an intensional system. We propose an algorithm called NMPL that improves the multiple predicate learning system MPL and extends its language from definite to this class of normal programs. Finally, we discuss the cost of the MPLs refinement algorithm and present theoretical and experimental results showing that NMPL can be as effective as MPL and is computationally cheaper than it.

Evaluation and improvements of clustering algorithms for detecting remote homologous protein families

BackgroundAn important problem in computational biology is the automatic detection of protein families (groups of homologous sequences). Clustering sequences into families is at the heart of most comparative studies dealing with protein evolution, structure, and function. Many methods have been developed for this task, and they perform reasonably well (over 0.88 of F-measure) when grouping proteins with high sequence identity. However, for highly diverged proteins the performance of these methods can be much lower, mainly because a common evolutionary origin is not deduced directly from sequence similarity. To the best of our knowledge, a systematic evaluation of clustering methods over distant homologous proteins is still lacking.ResultsWe performed a comparative assessment of four clustering algorithms: Markov Clustering (MCL), Transitive Clustering (TransClust), Spectral Clustering of Protein Sequences (SCPS), and High-Fidelity clustering of protein sequences (HiFix), considering several datasets with different levels of sequence similarity. Two types of similarity measures, required by the clustering sequence methods, were used to evaluate the performance of the algorithms: the standard measure obtained from sequence–sequence comparisons, and a novel measure based on profile-profile comparisons, used here for the first time.ConclusionsThe results reveal low clustering performance for the highly divergent datasets when the standard measure was used. However, the novel measure based on profile-profile comparisons substantially improved the performance of the four methods, especially when very low sequence identity datasets were evaluated. We also performed a parameter optimization step to determine the best configuration for each clustering method. We found that TransClust clearly outperformed the other methods for most datasets. This work also provides guidelines for the practical application of clustering sequence methods aimed at detecting accurately groups of related protein sequences.

ILP Through Propositionalization and Stochastic k-Term DNF Learning

One promising family of search strategies to alleviate runtime and storage requirements of ILP systems is that of stochastic local search methods, which have been successfully applied to hard propositional tasks such as satisfiability. Stochastic local search algorithms for propositional satisfiability benefit from the ability to quickly test whether a truth assignment satisfies a formula. Because of that many possible solutions can be tested and scored in a short time. In contrast, testing whether a clause covers an example in ILP takes much longer, so that far fewer possible solutions can be tested in the same time. Therefore in this paper we investigate stochastic local search in ILP using a relational propositionalized problem instead of directly use the first-order clauses space of solutions.