Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Stefan Westberg"'
Autor:
Michael Hampo, Trevor J. Bihl, Todd Jenkins, David Fan, Tarek M. Taha, Stefan Westberg, Ashley DeMange
Publikováno v:
ICONS
Implementing cognitive algorithms on robots is one potential direction to realize autonomous artificial agents. As society and technology progress there is an effort to push robotics and artificial intelligence into many aspects of daily life. An imp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ec351ce2fabb276d1e08a33a0dc26dcc
https://doi.org/10.1145/3407197.3407602
https://doi.org/10.1145/3407197.3407602
Publikováno v:
2019 IEEE National Aerospace and Electronics Conference (NAECON).
Hand tuning convolutional neural networks (CNN) for performance optimization can be tedious. A novel approach using a genetic algorithm to automate CNN hyper-parameter adjustment is proposed. This automated approach shows a 5% accuracy improvement ov
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d7016ea0795fc95a702ed528c6668b8
https://doi.org/10.1109/naecon46414.2019.9058307
https://doi.org/10.1109/naecon46414.2019.9058307
Autor:
Abdul A. S. Awwal, Mst Shamima Nasrin, Paheding Sidike, Mahmudul Hasan, Chris Yakopcic, Stefan Westberg, Zahangir Alom, Vijayan K. Asari, Brian Van Essen, Tarek M. Taha
Publikováno v:
Electronics, Vol 8, Iss 3, p 292 (2019)
In recent years, deep learning has garnered tremendous success in a variety of application domains. This new field of machine learning has been growing rapidly and has been applied to most traditional application domains, as well as some new areas th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8d357a7eeddb9ce2380b8e79ba9aa1e
http://www.mdpi.com/2079-9292/8/3/292
http://www.mdpi.com/2079-9292/8/3/292
Autor:
Anthony Reiling, Stefan Westberg, Eric J. Balster, Tarek M. Taha, Kerry L. Hill, William Mitchell
Publikováno v:
NAECON 2018 - IEEE National Aerospace and Electronics Conference.
Convolutional neural networks (CNNs) have gained prominence with image classification and other related tasks, often outperforming humans. However, many CNNs require significant power to function. Power modeling tells how much power a particular CNN
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7db551bad5e4a9c339b92a8ad62ce6f
https://doi.org/10.1109/naecon.2018.8556639
https://doi.org/10.1109/naecon.2018.8556639
Autor:
Stefan Westberg, Ulf Björkenstam
Publikováno v:
Computer-Aided Design. 19:58-64
The parametric cubic segment is the most commonly used curve segment in computer-aided design. Most CAD systems have what is called a spline routine to automate the definition of curves built up from several parametric cubic segments. A spline routin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d455acde50e80ea8d7b7044137d5bde
https://doi.org/10.1016/s0010-4485(87)80046-5
https://doi.org/10.1016/s0010-4485(87)80046-5
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.