Zobrazeno 1 - 10
of 1 407
pro vyhledávání: '"Burrello, A."'
Autor:
Hamdi, Mohamed Amine, Daghero, Francesco, Sarda, Giuseppe Maria, Van Delm, Josse, Symons, Arne, Benini, Luca, Verhelst, Marian, Pagliari, Daniele Jahier, Burrello, Alessio
Streamlining the deployment of Deep Neural Networks (DNNs) on heterogeneous edge platforms, coupling within the same micro-controller unit (MCU) instruction processors and hardware accelerators for tensor computations, is becoming one of the crucial
Externí odkaz:
http://arxiv.org/abs/2410.08855
Autor:
Risso, Matteo, Goffi, Alessia, Motetti, Beatrice Alessandra, Burrello, Alessio, Bove, Jean Baptiste, Macii, Enrico, Poncino, Massimo, Pagliari, Daniele Jahier, Maffeis, Giuseppe
Very High Resolution (VHR) geospatial image analysis is crucial for humanitarian assistance in both natural and anthropogenic crises, as it allows to rapidly identify the most critical areas that need support. Nonetheless, manually inspecting large a
Externí odkaz:
http://arxiv.org/abs/2410.04802
The demand for executing Deep Neural Networks (DNNs) with low latency and minimal power consumption at the edge has led to the development of advanced heterogeneous Systems-on-Chips (SoCs) that incorporate multiple specialized computing units (CUs),
Externí odkaz:
http://arxiv.org/abs/2409.18566
Autor:
Burrello, Alessio, Carlucci, Francesco, Pollo, Giovanni, Wang, Xiaying, Poncino, Massimo, Macii, Enrico, Benini, Luca, Pagliari, Daniele Jahier
PPG-based Blood Pressure (BP) estimation is a challenging biosignal processing task for low-power devices such as wearables. State-of-the-art Deep Neural Networks (DNNs) trained for this task implement either a PPG-to-BP signal-to-signal reconstructi
Externí odkaz:
http://arxiv.org/abs/2409.07485
The continuous improvement of fabrication techniques and high-quality semiconductor-superconductor interfaces allowed for unprecedented tunability of Josephson junction arrays (JJA), making them a promising candidate for analog quantum simulations of
Externí odkaz:
http://arxiv.org/abs/2408.14549
Autor:
Scherer, Moritz, Macan, Luka, Jung, Victor, Wiese, Philip, Bompani, Luca, Burrello, Alessio, Conti, Francesco, Benini, Luca
With the rise of Embodied Foundation Models (EFMs), most notably Small Language Models (SLMs), adapting Transformers for edge applications has become a very active field of research. However, achieving end-to-end deployment of SLMs on microcontroller
Externí odkaz:
http://arxiv.org/abs/2408.04413
Autor:
Wiese, Philip, İslamoğlu, Gamze, Scherer, Moritz, Macan, Luka, Jung, Victor J. B., Burrello, Alessio, Conti, Francesco, Benini, Luca
One of the challenges for Tiny Machine Learning (tinyML) is keeping up with the evolution of Machine Learning models from Convolutional Neural Networks to Transformers. We address this by leveraging a heterogeneous architectural template coupling RIS
Externí odkaz:
http://arxiv.org/abs/2408.02473
Autor:
Motetti, Beatrice Alessandra, Risso, Matteo, Burrello, Alessio, Macii, Enrico, Poncino, Massimo, Pagliari, Daniele Jahier
The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory occupatio
Externí odkaz:
http://arxiv.org/abs/2407.01054
Autor:
Benfenati, Luca, Ingolfsson, Thorir Mar, Cossettini, Andrea, Pagliari, Daniele Jahier, Burrello, Alessio, Benini, Luca
This study presents a novel approach for EEG-based seizure detection leveraging a BERT-based model. The model, BENDR, undergoes a two-phase training process. Initially, it is pre-trained on the extensive Temple University Hospital EEG Corpus (TUEG),
Externí odkaz:
http://arxiv.org/abs/2406.19189
Autor:
Daghero, Francesco, Burrello, Alessio, Poncino, Massimo, Macii, Enrico, Pagliari, Daniele Jahier
Depthwise separable convolutions are a fundamental component in efficient Deep Neural Networks, as they reduce the number of parameters and operations compared to traditional convolutions while maintaining comparable accuracy. However, their low data
Externí odkaz:
http://arxiv.org/abs/2406.12478