2 papers
cs.LG2018
Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures
Martin Mundt, Sagnik Majumder, Tobias Weis +1
We characterize convolutional neural networks with respect to the relative amount of features per layer. Using a skew normal distribution as a parametrized framework, we investigat…
cs.CV2017
Building effective deep neural network architectures one feature at a time
Martin Mundt, Tobias Weis, Kishore Konda +1
Successful training of convolutional neural networks is often associated with sufficiently deep architectures composed of high amounts of features. These networks typically rely on…