38 citations · 60 across the 4 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2016★ 11 cited
Efficient Dictionary Learning with Sparseness-Enforcing Projections
Markus Thom, Matthias Rapp, Günther Palm
Learning dictionaries suitable for sparse coding instead of using engineered bases has proven effective in a variety of image processing tasks. This paper studies the optimization…
cs.LG2016★ 38 cited
Sparse Activity and Sparse Connectivity in Supervised Learning
Markus Thom, Günther Palm
Sparseness is a useful regularizer for learning in a wide range of applications, in particular in neural networks. This paper proposes a model targeted at classification tasks, whe…
cs.LG2015★ 8 cited
Rapid Exact Signal Scanning with Deep Convolutional Neural Networks
Markus Thom, Franz Gritschneder
A rigorous formulation of the dynamics of a signal processing scheme aimed at dense signal scanning without any loss in accuracy is introduced and analyzed. Related methods propose…