Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Benedikt Pfülb"'
Publikováno v:
IEEE Transactions on Network and Service Management. 17:2662-2676
We present a processing pipeline for flow-based traffic classification using a machine learning component leveraging Deep Neural Networks (DNNs). The system is trained to predict likely characteristics of real-world traffic flows from a campus networ
Autor:
Benedikt Pfülb, Natalie Kiesler
Publikováno v:
Koli Calling
Unfortunately, the Boolean data type is still used in teaching and learning scenarios as default for the distinction of male or female gender. This paper focuses on the identification of the challenges associated with assigning binary gender identiti
Autor:
Benedikt Pfülb, Alexander Gepperth
Publikováno v:
IJCNN
We present Gaussian Mixture Replay (GMR), a rehearsal-based approach for continual learning (CL) based on Gaussian Mixture Models (GMM). CL approaches are intended to tackle the problem of catastrophic forgetting (CF), which occurs for Deep Neural Ne
Autor:
Benedikt Pfülb
Publikováno v:
EDULEARN Proceedings.
Autor:
Alexander Gepperth, Benedikt Pfülb
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2020 ISBN: 9783030616151
ICANN (2)
ICANN (2)
This work presents a mathematical treatment of the relation between Self-Organizing Maps (SOMs) and Gaussian Mixture Models (GMMs). We show that energy-based SOM models can be interpreted as performing gradient descent, minimizing an approximation to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::03c9d7a10383c4b69b827bb47b5e2973
https://doi.org/10.1007/978-3-030-61616-8_69
https://doi.org/10.1007/978-3-030-61616-8_69
Autor:
Alexander Gepperth, Benedikt Pfülb
We present an approach for efficiently training Gaussian Mixture Model (GMM) by Stochastic Gradient Descent (SGD) with non-stationary, high-dimensional streaming data. Our training scheme does not require data-driven parameter initialization (e.g., k
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1b6fd034549395292eba5f702f2337e
http://arxiv.org/abs/1912.09379
http://arxiv.org/abs/1912.09379
Publikováno v:
CNSM
We present a processing pipeline for flow-based throughput classification based on a machine learning component using deep neural networks (DNNs) that is trained to predict the likely bit rate of a real-world network traffic flow ahead of time. The D
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series ISBN: 9783030304898
ICANN (4)
ICANN (4)
We present a study of deep learning applied to the domain of network traffic data forecasting. This is a very important ingredient for network traffic engineering, e.g., intelligent routing, which can optimize network performance, especially in large
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c73345f6a3ca4e76af38c663f93c92a2
https://doi.org/10.1007/978-3-030-30490-4_40
https://doi.org/10.1007/978-3-030-30490-4_40
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2018 ISBN: 9783030014179
We investigate the performance of DNNs when trained on class-incremental visual problems consisting of initial training, followed by retraining with added visual classes. Catastrophic forgetting (CF) behavior is measured using a new evaluation proced
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de47f6f580b4212c408704c8a0b549c3
https://doi.org/10.1007/978-3-030-01418-6_48
https://doi.org/10.1007/978-3-030-01418-6_48
Autor:
Benedikt Pfülb
Publikováno v:
Benedikt Pfülb
knowledge is deeply grounded in many computer-based applications. An important research area of Artificial Intelligence (AI) deals with the automatic derivation of knowledge from data. Machine learning offers the according algorithms. One area of res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::cfb16f4ab2514b66ad372d1fdc033d4d
https://fuldok.hs-fulda.de/opus4/files/955/Dissertation.pdf
https://fuldok.hs-fulda.de/opus4/files/955/Dissertation.pdf