Recurrent neural nets - Open Access .click

IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018
Machine learning tools and semi-empirical models have been very successful in describing and predicting instantaneous climatic influences on the spatial and seasonal variability of biosphere state and function. Yet, little work has been carried to explicitly model dynamic features accounting for memory effects, where in some cases hand-designed ...
Markus Reichstein, Simon Besnard, Basil Kraft +2 more
exaly +4 more sources

Unsupervised Feature Learning Using Recurrent Neural Nets for Segmenting Hyperspectral Images

IEEE Geoscience and Remote Sensing Letters, 2021
Although deep learning is gaining more widespread use in hyperspectral image analysis, it is challenging to train high-capacity models in a supervised way--ground-truth sets are expensive to obtain, and they are practically always extremely imbalanced.
Michal Kawulok, Jakub Nalepa, Łukasz Tulczyjew +2 more
exaly +2 more sources

A Structure Theory for Identification of Recurrent Neural Nets - Part 1

IFAC Postprint Volumes IPPV / International Federation of Automatic Control, 1998
Abstract This paper extends some results on identifiability of recurrent (dynamic) neural nets obtained by F.Albertini and E.Sontag. A topological and geometrical description of the set of identifiable paranleters is given. In addition it is shown that the classes of observationally equivalent non-nlinimal systems are essentially finite unions of ...
Monika Dörfler, Manfred Deistler
exaly +2 more sources

fos: computer and information sciences
deep learning
convolutional neural nets

feature extraction
learning artificial intelligence
machine learning cs.lg

computer science - machine learning
neural and evolutionary computing cs.ne
machine learning