1

Truncated Variational Sampling for ‘Black Box’ Optimization of Generative Models

We investigate the optimization of two probabilistic generative models with binary latent variables using a novel variational EM approach. The approach distinguishes itself from previous variational approaches by using latent states as variational …

Solid Harmonic Wavelet Scattering: Predicting Quantum Molecular Energy from Invariant Descriptors of 3D Electronic Densities

We introduce a solid harmonic wavelet scattering representation, which is invariant to rigid movements and stable to deformations, for regression and classification of 2D and 3D images. Solid harmonic wavelets are computed by multiplying solid …

What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach

We study optimal image encoding based on a generative approach with non-linear feature combinations and explicit position encoding. By far most approaches to unsupervised learning learning of visual features, such as sparse coding or ICA, account for …

Learning invariant features by harnessing the aperture problem

The energy model is a simple, biologically inspired approach to extracting relationships between images in tasks like stereopsis and motion analysis. We discuss how adding an extra pooling layer to the energy model makes it possible to learn …

Ternary Sparse Coding

We study a novel sparse coding model with discrete and symmetric prior distribution. Instead of using continuous latent variables distributed according to heavy tail distributions, the latent variables of our approach are discrete. In contrast to …

Discrete Symmetric Priors for Sparse Coding

A standard model to explain the receptive fields of simple cells in the primary visual cortex is Sparse Coding (SC) [1]. However, the update equations used to train this model are not derivable in closed form. As a consequence, most state-of-the-art …