Gated networks are networks that contain gating connections in which the output of at least two neurons are multiplied. The basic idea of a gated restricted Boltzmann machine (RBM) model is to use the binary hidden units to learn the conditional distribution of one image (the output) given another image (the input). This allows the hidden units of a gated RBM to model the transformations between two successive images. Inference in the model consists in extracting the transformations given a pair of images. However, a fully connected multiplicative network creates cubically many parameters, forming a three-dimensional interaction tensor that requires a lot of memory and computations for inference and training. In this paper, we parameterize the bilinear interactions in the gated RBM through a multimodal tensor-based Tucker decomposition. Tucker decomposition decomposes a tensor into a set of matrices and one (usually smaller) core tensor. The parameterization through Tucker decomposition helps reduce the number of model parameters, reduces the computational costs of the learning process and effectively strengthens the structured feature learning. When trained on affine transformations of still images, we show how a completely unsupervised network learns explicit encodings of image transformations.

No abstract

This paper presents the performance analysis of preprocessing algorithms for enhancement features on mammograms with the objective of improving future clustering processing investigations, space frequency filtering and morphologic space filtering, which are analyzed with their different techniques in regions of interest using the DDSM database. Displaying microcalcifications, which is achieved with the Gaussian high-pass filter in the space frequency and diamond filter, in morphologic space, supported by spectral images (spectrograms) as well as the efficiency, is measured over massive preprocessing images. However, when an improved visualization is presented in processing times, it is observed that the variance in time analyzes a large number of images. Also, although the frequency is faster than morphological space, the morphological filters (Ball filtering) shows a significant result than frequency filters.

One of the main tasks in kernel methods is the selection of adequate mappings into higher dimension in order to improve class classification. However, this tends to be time consuming, and it may not finish with the best separation between classes. Therefore, there is a need for better methods that are able to extract distance and class separation from data. This work presents a novel approach for learning such mappings by using locally stationary kernels, spectral representations and Gaussian mixtures.