Learn More
The Bioconductor project is an initiative for the collaborative creation of extensible software for computational biology and bioinformatics. The goals of the project include: fostering collaborative development and widespread use of innovative software, reducing barriers to entry into interdisciplinary scientific research, and promoting the achievement of(More)
This paper rigorously establishes thut standard rnultiluyer feedforward networks with as f&v us one hidden layer using arbitrary squashing functions ure capable of upproximating uny Bore1 measurable function from one finite dimensional space to another to any desired degree of uccuracy, provided sujficirntly muny hidden units are available. In this sense,(More)
Recursive binary partitioning is a popular tool for regression analysis. Two fundamental problems of exhaustive search procedures usually applied to fit such models have been known for a long time: Overfitting and a selection bias towards covariates with many possible splits or missing values. While pruning procedures are able to solve the overfitting(More)
We consider the problem of learning from examples in layered linear feed-forward neural networks using optimization methods, such as back propagation, with respect to the usual quadratic error function E of the connection weights. Our main result is a complete description of the landscape attached to E in terms of principal component analysis. We show that(More)
-We show that standard multilayer feedfbrward networks with as few as a single hidden layer and arbitrary bounded and nonconstant activation function are universal approximators with respect to LP(lt) performance criteria, for arbitrary finite input environment measures p, provided only that sufficiently many hidden units are available. If the activation(More)
-We give conditions ensuring that multilayer jeedJorward networks with as Jew as a single hidden layer and an appropriately smooth hidden layer activation fimction are capable o f arbitrarily accurate approximation to an arbitrao' function and its derivatives. In fact, these networks can approximate functions that are not dtifferentiable in the classical(More)
This article is a (slightly) modified and shortened version of Grün and Hornik (2011), published in the Journal of Statistical Software. Topic models allow the probabilistic modeling of term frequency occurrences in documents. The fitted model can be used to estimate the similarity between documents as well as between a set of specified keywords using an(More)
We show that standardfeedforward networks with asl ew as a single hidden layer can uniformly approximate continuousfunctions on compacta provided that the activation function if; is locally R iemann integrable andnonpolynomial, and have universal LP(Jl)approximation capabilities for finite and compactly supportedinput environment measures JL provided that(More)