Zobrazeno 1 - 10 of 73 pro vyhledávání: '"Nina S T Hirata"'
1
Akademický článek
The information of attribute uncertainties: what convolutional neural networks can learn about errors in input data
Autor: Natália V N Rodrigues, L Raul Abramo, Nina S T Hirata
Publikováno v: Machine Learning: Science and Technology, Vol 4, Iss 4, p 045019 (2023)
Errors in measurements are key to weighting the value of data, but are often neglected in machine learning (ML). We show how convolutional neural networks (CNNs) are able to learn about the context and patterns of signal and noise, leading to improve
Externí odkaz: https://doaj.org/article/1c9e036057d74ab7a1db9b3f611006aa
Zobrazit plný text záznamu
2
Akademický článek
On Machine-Learning Morphological Image Operators
Autor: Nina S. T. Hirata, George A. Papakostas
Publikováno v: Mathematics, Vol 9, Iss 16, p 1854 (2021)
Morphological operators are nonlinear transformations commonly used in image processing. Their theoretical foundation is based on lattice theory, and it is a well-known result that a large class of image operators can be expressed in terms of two bas
Externí odkaz: https://doaj.org/article/d94db7dc7f964ff68fc98778ebf25005
Zobrazit plný text záznamu
7
Reducing the need for bounding box annotations in object detection using image classification data
Autor: Leonardo Blanger, Nina S. T. Hirata, Xiaoyi Jiang
We address the problem of training Object Detection models using significantly less bounding box annotated images. For that, we take advantage of cheaper and more abundant image classification data. Our proposal consists in automatically generating a
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82596014f9389da595f11d335bbf13bd
Zobrazit plný text záznamu
8
A new sample of southern radio galaxies: host-galaxy masses and star-formation rates
Autor: L. J. de Melo de Azevedo, L. Katena, Antonio Kanaan, Paula Coelho, M. V. Costa-Duarte, F. Urrutia-Viscarra, A. Schnorr Müller, Irapuan Rodrigues, Erik V.R. de Lima, Angela Krabbe, David Alexander Kann, M. Vika, Carlos Gabriel Escudero, S. Alencar, Dennis Zaritsky, Nina S. T. Hirata, G. Damke, Fernando Roig, H. Farías, Leonardo A. Almeida, Anthony H. Gonzalez, D. Brito-Silva, Favio Raúl Faifer, F. Almeida-Fernandes, Luca Izzo, H. J. Rocha Pinto, O. L. Dors, W. A. Santos, M. Jaque Arancibia, Rafael M. Santucci, Pieter Westera, Yara L. Jaffé, Bruno Quint, Kanak Saha, R. S. Nemmen, Roberto K. Saito, L. A. Gutiérrez-Soto, Silvia Rossi, Leandro Alberto Sesto, Lilianne Mariko Izuti Nakazono, Ana L. Chies-Santos, L. Azanha, C. Labayru, Christina C. Thöne, William Schoenell, C. Lima-Dias, A. de Ugarte Postigo, S. S. Eikenberry, Carlos A. Fernandes, E. A. Hartmann, R. A. Ortega-Minakata, L. Sampedro, Ramachrisna Teixeira, P. Amram, Daniela Lazzaro, N. Muñoz-Elgueta, R. Lopes de Oliveira, C. H. Veiga, E. Pattaro, Teresa Santos-Silva, C. B. Pereira, S. V. Werner, R. Cid Fernandes, F. R. Herpich, Alexandre S. Oliveira, Simone Daflon, R. S. de Souza, J. S. Alcaniz, Analia Viviana Smith Castelli, Beatriz B. Siffert, D. F. De Paula, C. Bonatto, H. D. Perottoni, Marina Trevisan, Y. Jimenez-Teja, Eduardo S. Pereira, L. Sodré, Timothy C. Beers, M. Borges Fernandes, A. Werle, M. L. Buzzo, C. Mendes de Oliveira, M. Castejon, Vinicius M. Placco, Richard L. Donnerstein, Javier Alonso-García, Roderik Overzier, S. Bonoli, J. A. Hernandez-Jimenez, C. Queiroz, Beatriz Luci Fernandes, Rodolfo H. Barbá, R. Monteiro-Oliveira, Thiago S. Gonçalves, R. Silva, Alvaro Alvarez-Candal, Arianna Cortesi, G. Fabiano de Souza, Karín Menéndez-Delmestre, Eduardo S. Cypriano, T. Ribeiro, J. Caffer, Zach Cano, Martin Makler, S. Fontes, H. S. Xavier, C. L. Barbosa, V. Jatenco-Pereira, K. G. Diem, Amanda R. Lopes, M. L. L. Dantas, R. C. Thom de Souza, A. Galarza, Jane Gregorio-Hetem, J. L. Nilo Castellón, A. Z. Vitorelli, D. Ortíz, R. de Menezes, Denise R. Gonçalves, Reginaldo Bezerra dos Santos, Jordi Miralda-Escudé, J. D. Hernández-Fernández, R. A. Dupke, Alberto Molino, R. Magalhães, L. Riguccini, A. Campillay, Ribamar R. R. Reis, Leandro Kerber, Fabricio Ferrari, G. B. Lima Neto, Pedro H. Bernardinelli, Stavros Akras, V. Branco, Devin D. Whitten, Luis Raul Weber Abramo, P. M. Novais, Antonio D. Montero-Dorta, S. Torres-Flores, Eduardo Telles, J. M. Carvano, C. E. Barbosa, R. de la Reza, Paulo A. A. Lopes, Alessandro Ederoclite
Publikováno v: Monthly Notices of the Royal Astronomical Society. 489:3403-3411
In this study we define a new sample of distant powerful radio galaxies in order to study their host-galaxy properties and provide targets for future observations of HI absorption with new radio telescopes and to understand the fuelling and feedback
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b0680faa842ecd7e1661b26d0f27e1b6
https://doi.org/10.1093/mnras/stz2371
Zobrazit plný text záznamu
9
Towards a quantitative survey of dimension reduction techniques
Autor: Mateus Espadoto, Nina S. T. Hirata, Andreas Kerren, Rafael Messias Martins, Alexandru Telea
Publikováno v: Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual)
Universidade de São Paulo (USP)
instacron:USP
Dimensionality reduction methods, also known as projections, are frequently used in multidimensional data exploration in machine learning, data science, and information visualization. Tens of such techniques have been proposed, aiming to address a wi
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e35f7f651ac27ef61e7fd084a8422b3
Zobrazit plný text záznamu
10
Classification and photometric redshift estimation of quasars in photometric surveys
Autor: Nina S. T. Hirata, Stephen S. Eikenberry, L. M. Izuti Nakazono, Sarik Jeram, Roderik Overzier, Conceição Queiroz, Anthony H. Gonzalez, R. Abramo, C. Mendes de Oliveira
Publikováno v: Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual)
Universidade de São Paulo (USP)
instacron:USP
We present a machine learning methodology to separate quasars from galaxies and stars using data from S-PLUS in the Stripe-82 region. In terms of quasar classification, we achieved 95.49% for precision and 95.26% for recall using a Random Forest algo
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50bc1d956499ebed1c6763fb7713b85f
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje