Aktuelles

In a joint team between BMW and TUM, we investigate the robustness of Convolutional Neural Network (CNN) deployment on embedded systems, particularly the robustness against adversarial attacks in automotive application scenarios. In the paper titled "BreakingBED - Breaking Binary and Efficient Deep… [weiterlesen]

For autonomous grasping by a prosthetic hand, a binarized neural network on FPGA has been investigated, focusing on the trade-off between application quality, FPGA resources, and power consumption. Results have been accepted for publication at the prestigious International Conference on Robotics and… [weiterlesen]

In ihrer Mitgliederversammlung im Herbst 2020 wurde Prof. Herkersdorf zu einem neuen Mitglied der Deutschen Akademie der Technikwissenschaften (acatech) gewählt. Die acatech Mitglieder beraten Politik und Gesellschaft in Fragen der Technologiepolitik sowie der Technik-Wissenschaften und kümmern sich… [weiterlesen]

The paper titled "Sensor Fusion Neural Networks for Gesture Recognition on Low-Power Edge Devices" authored by Gabor Balazs, Mateusz Chmurski, Walter Stechele, and Mariusz Zubert has been accepted for presentation at the International Conference on Agents and Artificial Intelligence (ICAART 2021). … [weiterlesen]

Gabor Balazs received the best paper award for presenting his work at the IEEE International Conference on Machine Learning and Applications (ICMLA). His paper titled "Neural Architecture Search for Automotive Grid Fusion Networks Under Embedded Hardware Constraints" authored by Gabor Balazs and… [weiterlesen]

Our paper "HyVE: A Hybrid Voting-based Eviction Policy for Caches" was awarded the Best Paper Award at NORCAS 2020. The paper is authored by Akshay Srivatsa, Sebastian Nagel, Nael Fasfous, Nguyen Anh Vu Doan, Thomas Wild, and Andreas Herkersdorf. It proposes a novel cache eviction method, which… [weiterlesen]

After finishing their master theses, three new staff members recently joined LIS and started working for their doctoral degrees. Lars Nolte and Tim Twardzyk will be active in a project targeting the optimization of on chip communication within multi- and manycore processor architectures by… [weiterlesen]