Assigning confidence to molecular property prediction

Assigning Confidence Intervals to Neural Network Predictions

Abstract This report reviews three possible approaches to the assignment of confidence intervals to feed-forward neural networks, namely, bootstrap estimation, maximum likelihood estimation, and Bayesian statistics. The report concludes with a proposal for mixture modelling via Markov Chain Monte Carlo sampling to enable non-Gaussian variances to be modelled without introducing the bias caused ...

Ordering Translation Templates by Assigning Confidence Factors

TTL Translation Template Learner algorithm learns lexical level correspondences between two translation examples by using analog ical reasoning The sentences used as translation examples have similar and di erent parts in the source language which must correspond to the similar and di erent parts in the target language Therefore these corre spondences are learned as translation templates The le...

Support Information for: eMolTox: prediction of molecular toxicity with confidence

eMolTox: prediction of molecular toxicity with confidence Changge Ji, Fredrik Svensson, Azedine Zoufir and Andreas Bender Shanghai Engineering Research Center for Molecular Therapeutics and New Drug Development, School of Chemistry and Molecular Engineering, East China Normal University, Shanghai 200062 China, Center for Molecular Informatics, Department of Chemistry, Lensfield Road, Cambridge ...

Robust Framework to Combine Diverse Classifiers Assigning Distributed Confidence to Individual Classifiers at Class Level

We have presented a classification framework that combines multiple heterogeneous classifiers in the presence of class label noise. An extension of m-Mediods based modeling is presented that generates model of various classes whilst identifying and filtering noisy training data. This noise free data is further used to learn model for other classifiers such as GMM and SVM. A weight learning meth...

Selection of Molecular Descriptor Subsets for Property Prediction