Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Joaquim Campos"'
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 3, Pp 36-48 (2022)
We develop a novel 2D functional learning framework that employs a sparsity-promoting regularization based on second-order derivatives. Motivated by the nature of the regularizer, we restrict the search space to the span of piecewise-linear box splin
Externí odkaz:
https://doaj.org/article/f36bd026114b464d96c464e3af019023
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 1, Pp 295-309 (2020)
We develop an efficient computational solution to train deep neural networks (DNN) with free-form activation functions. To make the problem well-posed, we augment the cost functional of the DNN by adding an appropriate shape regularization: the sum o
Externí odkaz:
https://doaj.org/article/979ba3bb38654d39a0ef599f579c2e81
Publikováno v:
Revista Brasileira de Zootecnia, Vol 28, Iss 6, Pp 1412-1418 (1999)
O objetivo deste trabalho foi avaliar o efeito de dietas com vários níveis de concentrado sobre o comportamento alimentar de cabras leiteiras. Dezoito cabras leiteiras Sem Raça Definida foram distribuídas em delineamento inteiramente casualizado
Externí odkaz:
https://doaj.org/article/95e28f7f2a4c44e7b9b718de944881e6
Publikováno v:
Revista Brasileira de Zootecnia, Vol 28, Iss 6, Pp 1419-1423 (1999)
O objetivo deste trabalho foi avaliar o hábito alimentar, consumo de matéria seca e desempenho em cabras alimentadas com fenos de rami (Boehemeria nivea G.), soja (Neonotonia wightii (L.) M.) e capim-elefante napier (Pennisetum purpureum Sch.), ofe
Externí odkaz:
https://doaj.org/article/da6110721d2f474bb045997222aac4b1
Publikováno v:
IEEE Transactions on Signal Processing
We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound of the actual Lipschitz constant of the input-output relation. To that
Publikováno v:
SSRN Electronic Journal.
Publikováno v:
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f7522aaea002db81a374a8a37cb3e51b
Publikováno v:
ICCV
While there are many deep learning based approaches for single image compression, the field of end-to-end learned video coding has remained much less explored. Therefore, in this work we present an inter-frame compression approach for neural video co
Autor:
Daniel Almeida, Juliana Bezerra Joaquim Campos, Rita Maria Lino Tarcia, Maria Elisabete Salvador, Silvio Carlos Coelho de Abreu, Celso Zilbovicius, Marco Antonio Manfredini
Publikováno v:
Apresentação Trabalhos Científicos.
Publikováno v:
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Mestrado em Engenharia Electrónica e Telecomunicações Neste trabalho é feita a análise matemática de um amplificador comutado auto-oscilante, considerando a existência de um atraso de propagação e/ou histerese no comparador, por forma a gara
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1b3175bb37f6b6e0dbcc5594c6c31bf5
http://hdl.handle.net/10773/7399
http://hdl.handle.net/10773/7399