Discriminative Training of Structured Dictionaries via Block Orthogonal Matching Pursuit

Abstract

It is well established that high-level representations learned via sparse coding are effective for many machine learning applications such as denoising and classification. In addition to being reconstructive, sparse representations that are discriminative and invariant can further help with such applications. In order to achieve these desired properties, this paper proposes a new framework that discriminatively trains structured dictionaries via block orthogonal matching pursuit. Specifically, the dictionary atoms are assumed to be organized into blocks. Distinct classes correspond to distinct blocks of dictionary atoms; however, our algorithm can handle the case where multiple classes share blocks. We provide theoretical justification and empirical evaluation of our method.

Learning to See: Convolutional Neural Networks for the Analysis of Social Science Data

“…A common procedure to set this number involves increasing the number of filters gradually through the network. Some scholars recommend to double the number of filters every time we add an additional (Shang et al 2016). Other architectures present even larger increments 10…”