In this paper, we focus on online representation learning in non-stationary environments which may require continuous adaptation of model’s architecture. We propose a novel online dictionary-learning (sparse-coding) framework which incorporates the addition and deletion of hidden units (dictionary elements), and is inspired by the adult neurogenesis phenomenon in the dentate gyrus of the hippoc...

Signal and image processing have seen in the last few years an explosion of interest in a new form of signal/image characterization via the concept of sparsity with respect to a dictionary. An active field of research is dictionary learning: Given a large amount of example signals/images one would like to learn a dictionary with much fewer atoms than examples on one hand, and much more atoms th...

A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement) probabilistic learning. After learning the deep convolutional dictionary, testing is implemented via deconvolutional inference. To speed up this inference, a new...

Designing an efficient over-complete dictionary is an important issue for developing a learning based system of super-resolution. To obtain fast solution, the size of dictionary needs to be reduced. However it may lower the performance as dictionary maybe incomplete. To address this issue, in this paper, we propose an improvement of dictionary learning for image super-resolution based on sparse...

Dictionary learning has became an increasingly important task in machine learning, as it is fundamental to the representation problem. A number of emerging techniques specifically include a codebook learning step, in which a critical knowledge abstraction process is carried out. Existing approaches in dictionary (codebook) learning are either generative (unsupervised e.g. k-means) or discrimina...

In this paper, we suggest to use a modified version of Smoothed0 (SL0) algorithm in the sparse representation step of iterative dictionary learning algorithms. In addition, we use a steepest descent for updating the non unit columnnorm dictionary instead of unit column-norm dictionary. Moreover, to do the dictionary learning task more blindly, we estimate the average number of active atoms in t...