Comparing biases for minimal network construction with back-propagation
Advances in neural information processing systems 1
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Dimensionality reduction and prior knowledge in E-set recognition
Advances in neural information processing systems 2
Advances in neural information processing systems 2
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Second Order Derivatives for Network Pruning: Optimal Brain Surgeon
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Computational models for neuroscience
WACV '02 Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision
Discovering the hidden structure of complex dynamic systems
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Evaluation of face recognition techniques using PCA, wavelets and SVM
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
Modern science is turning to progressively morecomplex and data-rich subjects, whichchallenges the existing methods of dataanalysis and interpretation. Consequently,there is a pressing need for development ofever more powerful methods of extracting orderfrom complex data and for automation of allsteps of the scientific process. VirtualScientist is a set of computational proceduresthat automate the method of inductive inferenceto derive a theory from observational datadominated by nonlinear regularities. Theprocedures utilize SINBAD – a novelcomputational method of nonlinear factoranalysis that is based on the principle ofmaximization of mutual information amongnon-overlapping sources, yielding higher-orderfeatures of the data that reveal hidden causalfactors controlling the observed phenomena. Theprocedures build a theory of the studiedsubject by finding inferentially useful hiddenfactors, learning interdependencies among itsvariables, reconstructing its functionalorganization, and describing it by a concisegraph of inferential relations among itsvariables. The graph is a quantitative model ofthe studied subject, capable of performingelaborate deductive inferences and explainingbehaviors of the observed variables bybehaviors of other such variables anddiscovered hidden factors. The set of Virtual Scientist procedures is a powerfulanalytical and theory-building tool designed tobe used in research of complex scientificproblems characterized by multivariate andnonlinear relations.