Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Tomotake Sasaki"'
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 16, Iss 1, Pp 349-362 (2023)
In many practical control applications, the performance level of a closed-loop system degrades over time due to the change of plant characteristics. Thus, there is a strong need for redesigning a controller without going through the system modelling
Externí odkaz:
https://doaj.org/article/fb4ac3311e67405ab87d667b9356413f
Publikováno v:
Scientific Reports, Vol 12, Iss 1, Pp 1-16 (2022)
Abstract Symmetry is omnipresent in nature and perceived by the visual system of many species, as it facilitates detecting ecologically important classes of objects in our environment. Yet, the neural underpinnings of symmetry perception remain elusi
Externí odkaz:
https://doaj.org/article/d1f72966b25947f0b1766a714171b401
Publikováno v:
Frontiers in Computational Neuroscience, Vol 16 (2022)
Biological learning systems are outstanding in their ability to learn from limited training data compared to the most successful learning machines, i.e., Deep Neural Networks (DNNs). What are the key aspects that underlie this data efficiency gap is
Externí odkaz:
https://doaj.org/article/4089c0182a6f4358a856117659f920d8
Autor:
Spandan Madan, Timothy Henry, Jamell Dozier, Helen Ho, Nishchal Bhandari, Tomotake Sasaki, Frédo Durand, Hanspeter Pfister, Xavier Boix
Publikováno v:
Nature Machine Intelligence. 4:146-153
Publikováno v:
IFAC-PapersOnLine. 55:16-21
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783031264115
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c61d2646006d12ed06dfec918e356ba3
https://doi.org/10.1007/978-3-031-26412-2_9
https://doi.org/10.1007/978-3-031-26412-2_9
Autor:
Frederico A. C. Azevedo, Xavier Boix, Kimberly Villalobos, Amineh Ahmadinejad, Tomotake Sasaki, Vilim Štih, Andrew Francl, Shobhita Sundaram, Jamell Dozier
The insideness problem is an aspect of image segmentation that consists of determining which pixels are inside and outside a region. Deep neural networks (DNNs) excel in segmentation benchmarks, but it is unclear if they have the ability to solve the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b26a20b2c347ccefe17df057a6e88aca
Autor:
Akira Sakai, Taro Sunagawa, Spandan Madan, Kanata Suzuki, Takashi Katoh, Hiromichi Kobashi, Hanspeter Pfister, Pawan Sinha, Xavier Boix, Tomotake Sasaki
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 155
The training data distribution is often biased towards objects in certain orientations and illumination conditions. While humans have a remarkable capability of recognizing objects in out-of-distribution (OoD) orientations and illuminations, Deep Neu
Publikováno v:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Stream-based active learning (AL) is an efficient training data collection method, and it is used to reduce human annotation cost required in machine learning. However, it is difficult to say that the human cost is low enough because most previous st
Publikováno v:
Frontiers in Computational Neuroscience, Vol 16 (2022)
Biological learning systems are outstanding in their ability to learn from limited training data compared to the most successful learning machines, i.e., Deep Neural Networks (DNNs). What are the key aspects that underlie this data efficiency gap is