no code implementations • 26 Dec 2023 • Jia Cheng Hu, Roberto Cavicchioli, Giulia Berardinelli, Alessandro Capotondi
Although the Transformer is currently the best-performing architecture in the homogeneous configuration (self-attention only) in Neural Machine Translation, many State-of-the-Art models in Natural Language Processing are made of a combination of different Deep Learning approaches.
2 code implementations • 20 May 2023 • Jia Cheng Hu, Roberto Cavicchioli, Alessandro Capotondi
The Image Captioning research field is currently compromised by the lack of transparency and awareness over the End-of-Sequence token (<Eos>) in the Self-Critical Sequence Training.
1 code implementation • 13 Aug 2022 • Jia Cheng Hu, Roberto Cavicchioli, Alessandro Capotondi
We introduce a method called the Expansion mechanism that processes the input unconstrained by the number of elements in the sequence.
Ranked #1 on Image Captioning on MS COCO
no code implementations • 7 Jul 2022 • Jia Cheng Hu, Roberto Cavicchioli, Alessandro Capotondi
Most recent state of the art architectures rely on combinations and variations of three approaches: convolutional, recurrent and self-attentive methods.
no code implementations • 20 Oct 2021 • Leonardo Ravaglia, Manuele Rusci, Davide Nadalini, Alessandro Capotondi, Francesco Conti, Luca Benini
In this work, we introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power (PULP) processor.
no code implementations • 12 Aug 2020 • Manuele Rusci, Marco Fariselli, Alessandro Capotondi, Luca Benini
The severe on-chip memory limitations are currently preventing the deployment of the most accurate Deep Neural Network (DNN) models on tiny MicroController Units (MCUs), even if leveraging an effective 8-bit quantization scheme.
no code implementations • 1 Jul 2020 • Miguel de Prado, Manuele Rusci, Romain Donze, Alessandro Capotondi, Serge Monnerat, Luca Benini and, Nuria Pazos
We leverage a family of compact and high-throughput tinyCNNs to control the mini-vehicle, which learn in the target environment by imitating a computer vision algorithm, i. e., the expert.
2 code implementations • 30 May 2019 • Manuele Rusci, Alessandro Capotondi, Luca Benini
To fit the memory and computational limitations of resource-constrained edge-devices, we exploit mixed low-bitwidth compression, featuring 8, 4 or 2-bit uniform quantization, and we model the inference graph with integer-only operations.
2 code implementations • 18 Dec 2017 • Andreas Kurth, Pirmin Vogel, Alessandro Capotondi, Andrea Marongiu, Luca Benini
Heterogeneous embedded systems on chip (HESoCs) co-integrate a standard host processor with programmable manycore accelerators (PMCAs) to combine general-purpose computing with domain-specific, efficient processing capabilities.
Hardware Architecture Distributed, Parallel, and Cluster Computing
no code implementations • 4 Dec 2017 • Paolo Meloni, Alessandro Capotondi, Gianfranco Deriu, Michele Brian, Francesco Conti, Davide Rossi, Luigi Raffo, Luca Benini
Deep convolutional neural networks (CNNs) obtain outstanding results in tasks that require human-level understanding of data, like image or speech recognition.