Zobrazeno 1 - 10 of 48 pro vyhledávání: '"Kanta TACHIBANA"'
3
Human action recognition method based on conformal geometric algebra and recurrent neural network
Autor: Nang Hung Van Nguyen, Phuc Do, Cong Thang Pham, Minh Tuan Pham, Kanta Tachibana
Publikováno v: Information and Control Systems. :2-11
Deep Learning (DL) plays an important role in machine learning and artificial intelligence. DL is widely applied in many fields with high dimensional data, including natural language processing, image recognition. High dimensional data can lead to pr
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a243b97bdd98b0418d7754779ab7c440
https://doi.org/10.31799/1684-8853-2020-5-2-11
Zobrazit plný text záznamu
7
Wind Prediction Performance of Complex Neural Network with ReLU Activation Function
Autor: Kanta Tachibana, Kentaro Otsuka
Publikováno v: 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).
The complex neural network expands on the complex plane more than the real neural network taking the real axis. So its figure transformation ability and learning speed are very good. However, the neural network needs to determine nonlinear transforma
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9469ae2adbd857e33cfc51b542d5e3ae
https://doi.org/10.23919/sice.2018.8492660
Zobrazit plný text záznamu
8
A Conformal Geometric Algebra Based Clustering Method and Its Applications
Autor: Kanta Tachibana, Minh Tuan Pham
Publikováno v: Advances in Applied Clifford Algebras. 26:1013-1032
Clustering is one of the most useful methods for understanding similarity among data. However, most conventional clustering methods do not pay sufficient attention to the geometric distributions of data. Geometric algebra (GA) is a generalization of
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fa899646fc0265c2d177412a7e97acac
https://doi.org/10.1007/s00006-015-0548-7
Zobrazit plný text záznamu
9
Effect of an Ensemble Algorithm in Reinforcement Learning for Garbage-Collection Sailing
Autor: Ryuta Fukazawa, Kanta Tachibana
Publikováno v: Robotic Sailing 2016 ISBN: 9783319454528
A robot sailor can obtain its behaviour autonomously with reinforcement learning. However, reinforcement learning suffers from the curse of dimensionality, with an increase in state variables and an exponential increase in the number of states to rea
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b77d26cf46043523ce358e9d8a18ac03
https://doi.org/10.1007/978-3-319-45453-5_7
Zobrazit plný text záznamu
10
Feature extraction for classification method using principal component based on conformal geometric algebra
Autor: Minh Tuan Pham, Kanta Tachibana, Phuc Hao Do
Publikováno v: IJCNN
This paper discusses feature extraction methods. The feature extraction methods such principal component analysis and multiple discriminant analysis are very important techniques in machine learning research areas. The characteristic of feature extra
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1bc6702bd8c636d65ea8378c7e7ad8d9
https://doi.org/10.1109/ijcnn.2016.7727735
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje