1 code implementation • 5 Feb 2024 • Florentia Afentaki, Michael Hefenbrock, Georgios Zervakis, Mehdi B. Tahoori
Due to the discrete nature of hardware approximation, we propose and implement a genetic-based, approximate, hardware-aware training approach specifically designed for printed MLPs.
no code implementations • 9 Jan 2024 • Soyed Tuhin Ahmed, Michael Hefenbrock, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
Bayesian Neural Networks (BayNNs) can inherently estimate predictive uncertainty, facilitating informed decision-making.
no code implementations • 27 Nov 2023 • Soyed Tuhin Ahmed, Kamal Danouchi, Michael Hefenbrock, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
In this paper, we propose the Scale Dropout, a novel regularization technique for Binary Neural Networks (BNNs), and Monte Carlo-Scale Dropout (MC-Scale Dropout)-based BayNNs for efficient uncertainty estimation.
1 code implementation • 15 Nov 2023 • Jörg K. H. Franke, Michael Hefenbrock, Gregor Koehler, Frank Hutter
Instead of applying a single constant penalty to all parameters, we enforce an upper bound on a statistical measure (e. g., the L$_2$-norm) of parameter groups.
no code implementations • 16 Jun 2023 • Soyed Tuhin Ahmed, Kamal Danouchi, Michael Hefenbrock, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
Furthermore, the number of dropout modules per network layer is reduced by a factor of $9\times$ and energy consumption by a factor of $94. 11\times$, while still achieving comparable predictive performance and uncertainty estimates compared to related works.
no code implementations • 15 Nov 2022 • Yiran Huang, Yexu Zhou, Michael Hefenbrock, Till Riedel, Likun Fang, Michael Beigl
In this work, we propose a pixel-wise decision-based attack algorithm that finds a distribution of adversarial perturbation through a reinforcement learning algorithm.
no code implementations • 4 Jan 2022 • Yiran Huang, Nicole Schaal, Michael Hefenbrock, Yexu Zhou, Till Riedel, Likun Fang, Michael Beigl
Our method leverages Monte Carlo tree search and models the process of generating explanations as two games.
no code implementations • 10 Aug 2020 • Yexu Zhou, Yuting Gao, Yiran Huang, Michael Hefenbrock, Till Riedel, Michael Beigl
An essential task in predictive maintenance is the prediction of the Remaining Useful Life (RUL) through the analysis of multivariate time series.