Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Konstantin Posch"'
Publikováno v:
Sensors, Vol 20, Iss 21, p 6011 (2020)
We present a novel approach for training deep neural networks in a Bayesian way. Compared to other Bayesian deep learning formulations, our approach allows for quantifying the uncertainty in model parameters while only adding very few additional para
Externí odkaz:
https://doaj.org/article/ff911f51e68d4382b721ce498f4fcf7f
Publikováno v:
Computers and Electronics in Agriculture. 162:364-372
The classification of different types of fruits and vegetables is a difficult task, since many types are quite similar in color and shape. In this study, we show an easy way to classify hyperspectral images with state of the art convolutional neural
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0786324520b3e8ecc54fe420ad901b85
https://doi.org/10.1016/j.compag.2019.04.019
https://doi.org/10.1016/j.compag.2019.04.019
Autor:
Konstantin Posch, Jürgen Pilz
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems
In this article, a novel approach for training deep neural networks using Bayesian techniques is presented. The Bayesian methodology allows for an easy evaluation of model uncertainty and, additionally, is robust to overfitting. These are commonly th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43ee145d52b4f02a65ac43a7e723d518
Accurate demand forecasting is one of the key aspects for successfully managing restaurants and staff canteens. In particular, properly predicting future sales of menu items allows a precise ordering of food stock. From an environmental point of view
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::77fde6632b5e789f1cd523418edf5a0f
Publikováno v:
Computational Statistics & Data Analysis
A novel Bayesian approach to the problem of variable selection in multiple linear regression models is proposed. In particular, a hierarchical setting which allows for direct specification of a priori beliefs about the number of nonzero regression co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f84e305b6a82b8d6f79949704545ccd8
http://arxiv.org/abs/1903.05367
http://arxiv.org/abs/1903.05367
Publikováno v:
Sensors
Volume 20
Issue 21
Sensors (Basel, Switzerland)
Sensors, Vol 20, Iss 6011, p 6011 (2020)
Volume 20
Issue 21
Sensors (Basel, Switzerland)
Sensors, Vol 20, Iss 6011, p 6011 (2020)
We present a novel approach for training deep neural networks in a Bayesian way. Compared to other Bayesian deep learning formulations, our approach allows for quantifying the uncertainty in model parameters while only adding very few additional para
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51d2f55b15818ddb72058c30ee832dca
https://doi.org/10.3390/s20216011
https://doi.org/10.3390/s20216011