Zobrazeno 1 - 10
of 1 024
pro vyhledávání: '"Zurada, Jacek M."'
This study aims to determine an optimal control strategy for vaccine scheduling in COVID-19 pandemic treatment by converting widely acknowledged infectious disease model named SEIR into an optimal control problem. The problem is augmented by adding m
Externí odkaz:
http://arxiv.org/abs/2008.10702
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of size (both
Externí odkaz:
http://arxiv.org/abs/1901.10900
The two key players in Generative Adversarial Networks (GANs), the discriminator and generator, are usually parameterized as deep neural networks (DNNs). On many generative tasks, GANs achieve state-of-the-art performance but are often unstable to tr
Externí odkaz:
http://arxiv.org/abs/1901.10824
Autor:
Ayinde, Babajide O., Zurada, Jacek M.
This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce a lot of r
Externí odkaz:
http://arxiv.org/abs/1802.07653
Autor:
Ayinde, Babajide O., Zurada, Jacek M.
Publikováno v:
IEEE Trans. on Neural Networks and Learning Systems, September 2018, Vol. 29, Issue 9, Pg. 3969 - 3979
Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially prominent when
Externí odkaz:
http://arxiv.org/abs/1802.00003
Publikováno v:
In Knowledge-Based Systems 5 December 2022 257
Publikováno v:
In Information Sciences March 2022 585:70-88
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. The learning algorithm is based on constraining negative weights. The p
Externí odkaz:
http://arxiv.org/abs/1601.02733
Publikováno v:
In Information Sciences April 2021 553:66-82