Experiments in Predicting Biodegradability

Blockeel, Hendrik; Džeroski, Sašo; Kompare, Boris; Krämer, Stefan; Pfahringer, Bernhard; Laer, Wim Van

doi:10.1080/08839510490279131

Cited by 21 publications

(34 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, predictive clustering trees have been used in an ILP setting. These trees can be used in a multi-task setting, where predictions for several tasks are made at every leaf (Blockeel et al 1998(Blockeel et al , 2004.…”

Section: Multi-task Learningmentioning

confidence: 99%

“…80.5 ± 6.2 7 2 .9 ± 4.3• 69.3 ± 3.9• 68.7 ± 3.0• NCTRER 78.5 ± 9.3 7 8 .0 ± 9.1 5 0 .9 ± 5.9• 65.1 ± 13.2 • Table 3 Result on the Biodegradability data set. The results for Tilde and S-CART have been taken from Blockeel et al (2004). 5 runs of 10 fold cross-validation have been performed, on the same splits into training and test set as used by Blockeel et al (2004).…”

Section: Comparison To Ilp and Propositionalization Approachesmentioning

confidence: 99%

“…It contains structural information (atoms and bonds) for a diverse set of natural, synthetic and environmental estrogens, and classifications with regard to their binding activity for the estrogen receptor. In the Biodegradability domain the task is to predict the biodegradability of chemical compounds based on their molecular structure and global molecular measurements (Blockeel et al 2004). The original (numeric) target variable is the half-life for aerobic aquenous biodegradation of the particular chemical compound.…”

Section: Experimental Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Fast learning of relational kernels

2010

View full text Add to dashboard Cite

We develop a general theoretical framework for statistical logical learning with kernels based on dynamic propositionalization, where structure learning corresponds to inferring a suitable kernel on logical objects, and parameter learning corresponds to function learning in the resulting reproducing kernel Hilbert space. In particular, we study the case where structure learning is performed by a simple FOIL-like algorithm, and propose alternative scoring functions for guiding the search process. We present an empirical evaluation on several data sets in the single-task as well as in the multi-task setting.

show abstract

Section: Multi-task Learningmentioning

confidence: 99%

Section: Comparison To Ilp and Propositionalization Approachesmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Fast learning of relational kernels

2010

View full text Add to dashboard Cite

show abstract

“…Examples of important applications of ILP must, at the very least, include domains such as music (Pompe et al, 1996;Tobudic & Widmer, 2003), the environment (Džeroski et al, 1995;Blockeel et al, 2004), intelligence analysis , and mathematical discovery (Colton & Muggleton, 2003;Todorovski et al, 2004).…”

Section: Applicationsmentioning

confidence: 99%

Induction as a Search Procedure

Konstantopoulos

Camacho

Fonseca

et al. 2008

Artificial Intelligence for Advanced Problem Solving Techniques

View full text Add to dashboard Cite

This chapter introduces Inductive Logic Programming (ILP) from the perspective of search algorithms in Computer Science. It first briefly considers the Version Spaces approach to induction, and then focuses on Inductive Logic Programming: from its formal definition and main techniques and strategies, to priors used to restrict the search space and optimized sequential, parallel, and stochastic algorithms. The authors hope that this presentation of the theory and applications of Inductive Logic Programming will help the reader understand the theoretical underpinnings of ILP, and also provide a helpful overview of the State-of-the-Art in the domain.

show abstract

“…For the experimental evaluation, we used four different real-world datasets, namely the NCI HIV dataset [3], a biodegradability dataset [11], and two mutagenicity datasets [12,7]. All these datasets contain a number of graphs describing chemical compounds.…”

Section: Datasetsmentioning

confidence: 99%

Don’t Be Afraid of Simpler Patterns

Bringmann

Zimmermann

Raedt

et al. 2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper investigates the trade-off between the expressiveness of the pattern language and the performance of the pattern miner in structured data mining. This trade-off is investigated in the context of correlated pattern mining, which is concerned with finding the k-best patterns according to a convex criterion, for the pattern languages of itemsets, multi-itemsets, sequences, trees and graphs. The criteria used in our investigation are the typical ones in data mining: computational cost and predictive accuracy and the domain is that of mining molecular graph databases. More specifically, we provide empirical answers to the following questions: how does the expressive power of the language affect the computational cost? and what is the trade-off between expressiveness of the pattern language and the predictive accuracy of the learned model? While answering the first question, we also introduce a novel stepwise approach to correlated pattern mining in which the results of mining a simpler pattern language are employed as a starting point for mining in a more complex one. This stepwise approach typically leads to significant speed-ups (up to a factor 1000) for mining graphs.

show abstract

Experiments in Predicting Biodegradability

Cited by 21 publications

References 15 publications

Fast learning of relational kernels

Fast learning of relational kernels

Induction as a Search Procedure

Don’t Be Afraid of Simpler Patterns

Contact Info

Product

Resources

About