Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Capotondi, Alessandro"'
Image Captioning is an important Language and Vision task that finds application in a variety of contexts, ranging from healthcare to autonomous vehicles. As many real-world applications rely on devices with limited resources, much effort in the fiel
Externí odkaz:
http://arxiv.org/abs/2408.13963
Autoregressive Sequence-To-Sequence models are the foundation of many Deep Learning achievements in major research fields such as Vision and Natural Language Processing. Despite that, they still present significant limitations. For instance, when err
Externí odkaz:
http://arxiv.org/abs/2408.13959
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 diff
Externí odkaz:
http://arxiv.org/abs/2312.15872
Memory interference may heavily inflate task execution times in Heterogeneous Systems-on-Chips (HeSoCs). Knowing worst-case interference is consequently fundamental for supporting the correct execution of time-sensitive applications. In most of the l
Externí odkaz:
http://arxiv.org/abs/2309.12864
The Image Captioning research field is currently compromised by the lack of transparency and awareness over the End-of-Sequence token () in the Self-Critical Sequence Training. If the token is omitted, a model can boost its performance up
Externí odkaz:
http://arxiv.org/abs/2305.12254
Autor:
Capotondi, Alessandro <1983>
The negotiation between power consumption, performance, programmability, and portability drives all computing industry designs, in particular the mobile and embedded systems domains. Two design paradigms have proven particularly promising in this con
Externí odkaz:
http://amsdottorato.unibo.it/7630/
Autor:
Valente, Luca, Tortorella, Yvan, Sinigaglia, Mattia, Tagliavini, Giuseppe, Capotondi, Alessandro, Benini, Luca, Rossi, Davide
IoT applications span a wide range in performance and memory footprint, under tight cost and power constraints. High-end applications rely on power-hungry Systems-on-Chip (SoCs) featuring powerful processors, large LPDDR/DDR3/4/5 memories, and suppor
Externí odkaz:
http://arxiv.org/abs/2211.14944
We introduce a method called the Expansion mechanism that processes the input unconstrained by the number of elements in the sequence. By doing so, the model can learn more effectively compared to traditional attention-based approaches. To support th
Externí odkaz:
http://arxiv.org/abs/2208.06551
Most recent state of the art architectures rely on combinations and variations of three approaches: convolutional, recurrent and self-attentive methods. Our work attempts in laying the basis for a new research direction for sequence modeling based up
Externí odkaz:
http://arxiv.org/abs/2207.03327
Autor:
Ravaglia, Leonardo, Rusci, Manuele, Nadalini, Davide, Capotondi, Alessandro, Conti, Francesco, Benini, Luca
Publikováno v:
IEEE Journal on Emerging and Selected Topics in Circuits and Systems 11.4 (2021), 789-802
In the last few years, research and development on Deep Learning models and techniques for ultra-low-power devices in a word, TinyML has mainly focused on a train-then-deploy assumption, with static models that cannot be adapted to newly collected da
Externí odkaz:
http://arxiv.org/abs/2110.10486