no code implementations • 30 Jan 2019 • Babajide O. Ayinde, Tamer Inanc, Jacek M. Zurada
It is shown that both network size and activation function are the two most important components that foster the tendency of DNNs to extract redundant features.
no code implementations • 30 Jan 2019 • Babajide O. Ayinde, Keishin Nishihama, Jacek M. Zurada
In addition to the gradient information from the adversarial loss made available by the discriminator, diversity regularization also ensures that a more stable gradient is provided to update both the generator and discriminator.
2 code implementations • 21 Feb 2018 • Babajide O. Ayinde, Jacek M. Zurada
This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters).
no code implementations • 31 Jan 2018 • Babajide O. Ayinde, Jacek M. Zurada
Unsupervised feature extractors are known to perform an efficient and discriminative representation of data.
no code implementations • 12 Jan 2016 • Ehsan Hosseini-Asl, Jacek M. Zurada, Olfa Nasraoui
We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data.