Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Michelangelo Diligenti"'
Publikováno v:
BMC Bioinformatics, Vol 20, Iss 1, Pp 1-14 (2019)
Abstract Background The advent of high-throughput experimental techniques paved the way to genome-wide computational analysis and predictive annotation studies. When considering the joint annotation of a large set of related entities, like all protei
Externí odkaz:
https://doaj.org/article/56c45242a2894bc5a4f3afeca5b710e9
Autor:
Maxime Mulamba, Michelangelo Diligenti, Victor Bucarey, Tias Guns, Michele Lombardi, Jayanta Mandi
Publikováno v:
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
IJCAI
IJCAI
Many decision-making processes involve solving a combinatorial optimization problem with uncertain input that can be estimated from historic data. Recently, problems in this class have been successfully addressed via end-to-end learning approaches, w
Neural-symbolic models bridge the gap between sub-symbolic and symbolic approaches, both of which have significant limitations. Sub-symbolic approaches, like neural networks, require a large amount of labeled data to be successful, whereas symbolic a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2bcf1f7fa8c6b2536eee884bf9710ffc
https://doi.org/10.3233/faia210355
https://doi.org/10.3233/faia210355
Publikováno v:
IEEE Transactions on Fuzzy Systems. 27:1407-1416
In this paper we introduce the convex fragment of {\L}ukasiewicz Logic and discuss its possible applications in different learning schemes. Indeed, the provided theoretical results are highly general, because they can be exploited in any learning fra
Deep Learning architectures can develop feature representations and classification models in an integrated way during training. This joint learning process requires large networks with many parameters, and it is successful when a large amount of trai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4bc4f36710197918d8f2d04b6a3c122d
http://hdl.handle.net/11365/1138590
http://hdl.handle.net/11365/1138590
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783030461461
ECML/PKDD (2)
ECML/PKDD (2)
Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns. Probabilistic logic reasoning, on the other hand, is capable to take consistent and r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::94dbcca6f9ea9017fd9845ffa00ee103
https://doi.org/10.1007/978-3-030-46147-8_31
https://doi.org/10.1007/978-3-030-46147-8_31
Injecting prior knowledge into the learning process of a neural architecture is one of the main challenges currently faced by the artificial intelligence community, which also motivated the emergence of neural-symbolic models. One of the main advanta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9141751fa70fab911962b0fb793ba6a1
http://arxiv.org/abs/1907.11468
http://arxiv.org/abs/1907.11468
Publikováno v:
Inductive Logic Programming ISBN: 9783030492090
ILP
ILP
Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing. A key element of this success has been the development of new loss functions, like the popular cross-entropy loss, whi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f10165615287306bc6c28bce0ff9c2d
http://arxiv.org/abs/1907.07904
http://arxiv.org/abs/1907.07904
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030305079
ICANN (3)
ICANN (3)
In the last few years the systematic adoption of deep learning to visual generation has produced impressive results that, amongst others, definitely benefit from the massive exploration of convolutional architectures. In this paper, we propose a gene
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a997195f6e86902f8e38a858de401db0
https://doi.org/10.1007/978-3-030-30508-6_45
https://doi.org/10.1007/978-3-030-30508-6_45
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783030461461
ECML/PKDD (2)
ECML/PKDD (2)
In spite of the amazing results obtained by deep learning in many applications, a real intelligent behavior of an agent acting in a complex environment is likely to require some kind of higher-level symbolic inference. Therefore, there is a clear nee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f3e015d562b49f5d2dc5942c8ce509b8