Zobrazeno 1 - 10
of 452
pro vyhledávání: '"Ascheid, Gerd"'
Our research investigates the challenges Deep Reinforcement Learning (DRL) faces in complex, Partially Observable Markov Decision Processes (POMDP) such as autonomous driving (AD), and proposes a solution for vision-based navigation in these environm
Externí odkaz:
http://arxiv.org/abs/2409.10554
One of the main reasons for the success of Evolutionary Algorithms (EAs) is their general-purposeness, i.e., the fact that they can be applied straightforwardly to a broad range of optimization problems, without any specific prior knowledge. On the o
Externí odkaz:
http://arxiv.org/abs/2103.16897
Autor:
Demir, Mehmet Özgün, Topal, Ozan Alp, Pusane, Ali Emre, Dartmann, Guido, Ascheid, Gerd, Kurt, Güneş Karabulut
Being capable of sensing and behavioral adaptation in line with their changing environments, cognitive cyber-physical systems (CCPSs) are the new form of applications in future wireless networks. With the advancement of the machine learning algorithm
Externí odkaz:
http://arxiv.org/abs/2101.02446
Autor:
Hallawa, Ahmed, Born, Thorsten, Schmeink, Anke, Dartmann, Guido, Peine, Arne, Martin, Lukas, Iacca, Giovanni, Eiben, A. E., Ascheid, Gerd
In this work, we propose a novel approach for reinforcement learning driven by evolutionary computation. Our algorithm, dubbed as Evolutionary-Driven Reinforcement Learning (evo-RL), embeds the reinforcement learning algorithm in an evolutionary cycl
Externí odkaz:
http://arxiv.org/abs/2007.04725
Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Increasingly sophisticated hardware accelerators are proposed that exploit e.g. the sparsity in computations and mak
Externí odkaz:
http://arxiv.org/abs/2006.12274
Autor:
Schorn, Christoph, Elsken, Thomas, Vogel, Sebastian, Runge, Armin, Guntoro, Andre, Ascheid, Gerd
Applying deep neural networks (DNNs) in mobile and safety-critical systems, such as autonomous vehicles, demands a reliable and efficient execution on hardware. Optimized dedicated hardware accelerators are being developed to achieve this. However, t
Externí odkaz:
http://arxiv.org/abs/1909.13844
In recent years, neural networks have surpassed classical algorithms in areas such as object recognition, e.g. in the well-known ImageNet challenge. As a result, great effort is being put into developing fast and efficient accelerators, especially fo
Externí odkaz:
http://arxiv.org/abs/1904.05106
Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled network models
Externí odkaz:
http://arxiv.org/abs/1611.06539
Publikováno v:
In Integration January 2020 70:10-20
It is common practice in wireless communications to assume strict or wide-sense stationarity of the wireless channel in time and frequency. While this approximation has some physical justification, it is only valid inside certain time-frequency regio
Externí odkaz:
http://arxiv.org/abs/1401.1138