Výsledky vyhledávání - "Edson C. Kitani"

An Acceleration Method based on Deep Learning and Multilinear Feature Space

Autor: Michel Andre L .Vinagreiro, Leopoldo Rideki Yoshioka, Armando Antônio Maria Laganá, Edson C. Kitani

Publikováno v: International Journal of Artificial Intelligence & Applications. 12:9-26

Computer vision plays a crucial role in Advanced Assistance Systems. Most computer vision systems are based on Deep Convolutional Neural Networks (deep CNN) architectures. However, the high computational resource to run a CNN algorithm is demanding.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::77751e6872f5d9b3a6359e564d196bba
https://doi.org/10.5121/ijaia.2021.12502

Zobrazit plný text záznamu

Fast Deep Learning Classification With Multilinear Feature Maps

Autor: Michel Vinagreiro, Edson C. Kitani, Armando Antonio Lagana, Leopoldo Rideki Yoshioka

Publikováno v: 2022 International Joint Conference on Neural Networks (IJCNN).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0b3647ad914e9779bd0e1631573d3056
https://doi.org/10.1109/ijcnn55064.2022.9892498

Zobrazit plný text záznamu

Using Multilinear Feature Space to Accelerate CNN Classification

Autor: Edson C. Kitani, Michel Andre L .Vinagreiro, Armando Antônio Maria Laganá, Leopoldo Rideki Yoshioka

Publikováno v: Computer Science & Information Technology (CS & IT).

Computer vision plays a crucial role in ADAS security and navigation, as most systems are based on deep CNN architectures the computational resource to run a CNN algorithm is demanding. Therefore, the methods to speed up computation have become a rel

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::26b42d50cdcc80172e3002b4688e6a01
https://doi.org/10.5121/csit.2021.111109

Zobrazit plný text záznamu

Teaching microcontrollers using automotive electronic systems

Autor: Bruno Arantes Dias, João F. Justo, Cynthia Thamires da Silva, Edson C. Kitani, Armando Antônio Maria Laganá

Publikováno v: Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual)
Universidade de São Paulo (USP)
instacron:USP

Teaching an undergraduate course on microcontrollers using real examples from automotive embedded electronics helped to motivate students. This course was implemented using a set of didactic kits, which allowed students to explore real applications.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::839e46108b1ae920b3632422302de9b5
https://doi.org/10.1177/0020720915596750

Zobrazit plný text záznamu

Mapeamento e visualização de dados em alta dimensão com mapas auto-organizados

Autor: Edson C. Kitani

Publikováno v: Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP

Os seres vivos têm uma impressionante capacidade de lidar com ambientes complexos com grandes quantidades de informações de forma muito autônoma. Isto os torna um modelo ideal para o desenvolvimento de sistemas artificiais bioinspirados. A rede n

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a15da1bb323eb1612a7ad17ecf89cba
https://doi.org/10.11606/t.3.2013.tde-11072014-114804

Zobrazit plný text záznamu

Fine-tuning of the SOMkNN classifier

Autor: Emilio Del-Moral-Hernandez, Edson C. Kitani, Leandro Augusto da Silva

Publikováno v: IJCNN

Classification is an important data mining task used in decision-making processes. Techniques such as Artificial Neural Networks (ANN) and Statistics are used to help in an automatic classification. In a previous work, we proposed a method for classi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::24e3dd730d8934c866f3248d7f4b3bc2
https://doi.org/10.1109/ijcnn.2013.6706972

Zobrazit plný text záznamu

Learning Embedded Data Structure with Self-Organizing Maps

Autor: Edson C. Kitani, Emilio Del-Moral-Hernandez, Leandro Augusto da Silva

Publikováno v: Advances in Intelligent Systems and Computing ISBN: 9783642352294
WSOM

Self-Organizing Map (SOM) is undoubtedly one of the most famous and successful artificial neural network approaches. Since the SOM is related with the Vector Quantization learning process, minimizing error quantization and maximizing topology preserv

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7fc67d6b8b5cdbe2f33d3031c728156a
https://doi.org/10.1007/978-3-642-35230-0_23

Zobrazit plný text záznamu

SOMM – Self-Organized Manifold Mapping

Autor: Leandro Augusto da Silva, Edson C. Kitani, Emilio Del-Moral-Hernandez

Publikováno v: Artificial Neural Networks and Machine Learning – ICANN 2012 ISBN: 9783642332654
ICANN (2)

The Self Organizing Map (SOM) [1] proposed by Kohonen has proved to be remarkable in terms of its range of applications. It can be used for high dimensional space visualization, pattern recognition, input space dimensionality reduction and for genera

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::8cc09ff1a0df6776137e07b20f4f320a
https://doi.org/10.1007/978-3-642-33266-1_44

Zobrazit plný text záznamu

A Multi-Linear Statistical Method for Discriminant Analysis of 2D Frontal Face Images

Autor: Vagner do Amaral, Carlos Eduardo Thomaz, Duncan Fyfe Gillies, Gilson A. Giraldi, Edson C. Kitani, João Ricardo Sato

This chapter describes a multi-linear discriminant method of constructing and quantifying statistically significant changes on human identity photographs. The approach is based on a general multivariate two-stage linear framework that addresses the s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4b9aef6272171d69441d991bf968d0a5
https://doi.org/10.4018/978-1-61350-429-1.ch002

Zobrazit plný text záznamu

Exploring and Understanding the High Dimensional and Sparse Image Face Space: a Self-Organized Manifold Mapping

Autor: Edson C. Kitani, Gilson A. Giraldi, Carlos Eduardo Thomaz, Emilio Del Moral Hernandez

Publikováno v: New Approaches to Characterization and Recognition of Faces

Face recognition has motivated several research studies in the last years owing not only to its applicability and multidisciplinary inherent characteristics, but also to its important role in human relationship. Despite extensive studies on face reco

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a7c6636980412a9c348b7f6b4b440ec3
https://doi.org/10.5772/22173

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání