Aktuelles

The paper titled "LCS-Based Automatic Configuration of Approximate Computing Parameters for FPGA System Designs" authored by Simon Conrady, Arne Kreddig, Manu Manuel and Walter Stechele has been accepted for publication at the International Workshop on Learning Classifier Systems (IWLCS). The paper… [weiterlesen]

On April 15 and 16, 2019 we organized SelPhyS 2019, the 4th edition of the workshop on applying self-awareness in the design of embedded and cyber-physical systems, in the Theresianum on the TUM City Campus. The concept of self-awareness is currently a hot research topic in many technical domains.… [weiterlesen]

Our authors A. Frickenstein, MR Vemparala, C. Unger, F. Ayar and W. Stechele got their paper titled "DSC Dense-Sparse Convolution for Vectorized Inference of Convolutional Neural Networks" accepted at the Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD). This workshop is held… [weiterlesen]

The paper "Resource-Aware Multicriterial Optimization of DNNs for Low-Cost Embedded Applications" authored by Alexander Frickenstein, Christian Unger and Walter Stechele, has been accepted at the 16th edition of the Conference on Computer and Robot Vision, which will take place from May 29 till 31,… [weiterlesen]

Prof. Herkersdorf gave an invited talk on self-aware MPSoC system optimization at the RAPIDO workshop of HiPEAC 2019 Conference in Valencia, Spain. The focus of the RAPIDO workshop is on methods and tools for rapid simulation and performance evaluation in embedded and high performance system design.… [weiterlesen]

To improve traffic safety, Deep Neural Networks (DNN) are being developed worldwide for automotive applications. The challenge is that DNNs are compute- and memory-intensive, but the computing capacity in the vehicle remains limited. Within the framework of this project methods of approximate… [weiterlesen]

Digital image processing in professional applications places ever-higher demands, so that the computing power and power consumption of FPGA devices reach their limits. Approximate Computing refers to a set of methods that are performing calculations not exactly but only approximately. As a benefit,… [weiterlesen]