We present a framework to apply Volterra series to analyze multilayered perceptrons trained to estimate the posterior probabilities of phonemes in automatic speech recognition. Th...
Joel Pinto, Garimella S. V. S. Sivaram, Hynek Herm...
Barycentric plotting, achieved by placing gaussian kernels in distant corners of the feature space and projecting multidimensional output of neural network on a plane, provides inf...
In many applications, high dimensional input data can be considered as sampled functions. We show in this paper how to use this prior knowledge to implement functional preprocessin...
— Over time, neural networks have proven to be extremely powerful tools for data exploration with the capability to discover previously unknown dependencies and relationships in ...