no code implementations • 30 Sep 2022 • Dominika Przewlocka-Rus, Tomasz Kryjak
Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e. g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e. g., quantisation, pruning, or dedicated lightweight architectures.
no code implementations • 21 May 2022 • Dominika Przewlocka-Rus, Tomasz Kryjak
To overcome this, one can use energy-efficient embedded devices, such as heterogeneous platforms joining the ARM processor system with programmable logic (FPGA).
no code implementations • 9 Mar 2022 • Dominika Przewlocka-Rus, Syed Shakib Sarwar, H. Ekin Sumbul, Yuecheng Li, Barbara De Salvo
Eventually, the experiments showed that for low bit width precision, non-uniform quantization performs better than uniform, and at the same time, PoT quantization vastly reduces the computational complexity of the neural network.
no code implementations • 6 Apr 2021 • Dominika Przewlocka-Rus, Marcin Kowalczyk, Tomasz Kryjak
Deep learning algorithms are a key component of many state-of-the-art vision systems, especially as Convolutional Neural Networks (CNN) outperform most solutions in the sense of accuracy.