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 • 23 Jan 2024 • Soyed Tuhin Ahmed, Kamal Danouchi, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
Bayesian Neural Networks (BayNNs) naturally provide uncertainty in their predictions, making them a suitable choice in safety-critical applications.
no code implementations • 11 Jan 2024 • Soyed Tuhin Ahmed, Kamal Danouchi, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
Internet of Things (IoT) and smart wearable devices for personalized healthcare will require storing and computing ever-increasing amounts of data.
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 • 2 Jan 2024 • Soyed Tuhin Ahmed, Mehdi B. Tahoori
During the online operation, by matching the uncertainty fingerprint, we can concurrently self-test NNs with up to $100\%$ coverage with a low false positive rate while maintaining a similar performance of the primary task.
1 code implementation • 2 Dec 2023 • Giorgos Armeniakos, Paula L. Duarte, Priyanjana Pal, Georgios Zervakis, Mehdi B. Tahoori, Dimitrios Soudris
Printed electronics (PE) technology provides cost-effective hardware with unmet customization, due to their low non-recurring engineering and fabrication costs.
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.
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 • 16 May 2023 • Soyed Tuhin Ahmed, Mehdi B. Tahoori
Neural networks (NNs) are capable of learning complex patterns and relationships in data to make predictions with high accuracy, making them useful for various tasks.
1 code implementation • 14 Mar 2023 • Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris, Mehdi B. Tahoori, Jörg Henkel
Printed electronics (PE) promises on-demand fabrication, low non-recurring engineering costs, and sub-cent fabrication costs.
1 code implementation • 28 Feb 2023 • Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris, Mehdi B. Tahoori, Jörg Henkel
Printed Electronics (PE) exhibits on-demand, extremely low-cost hardware due to its additive manufacturing process, enabling machine learning (ML) applications for domains that feature ultra-low cost, conformity, and non-toxicity requirements that silicon-based systems cannot deliver.
no code implementations • 2 Oct 2022 • Jörg Henkel, Hai Li, Anand Raghunathan, Mehdi B. Tahoori, Swagath Venkataramani, Xiaoxuan Yang, Georgios Zervakis
In this work, we enlighten the synergistic nature of AxC and ML and elucidate the impact of AxC in designing efficient ML systems.
no code implementations • 15 Mar 2022 • Konstantinos Balaskas, Georgios Zervakis, Kostas Siozios, Mehdi B. Tahoori, Joerg Henkel
Although Printed Electronics (PE) cannot compete with silicon-based systems in conventional evaluation metrics, e. g., integration density, area and performance, PE offers attractive properties such as on-demand ultra-low-cost fabrication, flexibility and non-toxicity.
1 code implementation • 11 Mar 2022 • Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris, Mehdi B. Tahoori, Jörg Henkel
In our extensive experimental evaluation we consider 14 MLPs and SVMs and evaluate more than 4300 approximate and exact designs.