Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Malossi, A. Cristiano I."'
Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or adversarial
Externí odkaz:
http://arxiv.org/abs/2310.00761
Autor:
Mariani, Giovanni, Zhu, Yada, Li, Jianbo, Scheidegger, Florian, Istrate, Roxana, Bekas, Costas, Malossi, A. Cristiano I.
Since decades, the data science community tries to propose prediction models of financial time series. Yet, driven by the rapid development of information technology and machine intelligence, the velocity of today's information leads to high market e
Externí odkaz:
http://arxiv.org/abs/1909.10578
Autor:
Sood, Atin, Elder, Benjamin, Herta, Benjamin, Xue, Chao, Bekas, Costas, Malossi, A. Cristiano I., Saha, Debashish, Scheidegger, Florian, Venkataraman, Ganesh, Thomas, Gegi, Mariani, Giovanni, Strobelt, Hendrik, Samulowitz, Horst, Wistuba, Martin, Manica, Matteo, Choudhury, Mihir, Yan, Rong, Istrate, Roxana, Puri, Ruchir, Pedapati, Tejaswini
Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice. Pre-trained neural network models available through APIs or capability to custom train pre-built neural network architecture
Externí odkaz:
http://arxiv.org/abs/1901.06261
Publikováno v:
Philosophical Transactions of the Royal Society A: Physical, Mathematical and Engineering Sciences. 372(2018)
Power awareness is fast becoming immensely important in computing, ranging from the traditional High Performance Computing applications, to the new generation of data centric workloads. In this work we describe our efforts towards a power efficient c
Externí odkaz:
http://arxiv.org/abs/1405.4644
Autor:
Kalantzis, Vassilis, Malossi, A. Cristiano I., Bekas, Costas, Curioni, Alessandro, Gallopoulos, Efstratios, Saad, Yousef
Publikováno v:
In Parallel Computing May 2018 74:136-153
Publikováno v:
In Journal of Computational Physics 15 October 2013 251:136-155
Publikováno v:
In Computer Methods in Applied Mechanics and Engineering 1 September 2012 237-240:212-226
Autor:
Schmidt, Maximilian, Bartezzaghi, Andrea, Bogojeska, Jasmina, Malossi, A. Cristiano I., Vu, Thang
Neural approaches have become very popular in the domain of Question Answering, however they require a large amount of annotated data. Furthermore, they often yield very good performance but only in the domain they were trained on. In this work we pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::597db9ea5214a7dc353f5fb1802ce17f
Publikováno v:
In Journal of Computational Physics 2011 230(8):3230-3248
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.