Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Kutsuna, Takuro"'
Autor:
Kutsuna, Takuro
Diffusion models have become fundamental tools for modeling data distributions in machine learning and have applications in image generation, drug discovery, and audio synthesis. Despite their success, these models face challenges when generating dat
Externí odkaz:
http://arxiv.org/abs/2412.03134
Domain incremental learning (DIL) has been discussed in previous studies on deep neural network models for classification. In DIL, we assume that samples on new domains are observed over time. The models must classify inputs on all domains. In practi
Externí odkaz:
http://arxiv.org/abs/2403.16707
Autor:
Kutsuna, Takuro
In this paper, we first identify activation shift, a simple but remarkable phenomenon in a neural network in which the preactivation value of a neuron has non-zero mean that depends on the angle between the weight vector of the neuron and the mean of
Externí odkaz:
http://arxiv.org/abs/2403.13833
Publikováno v:
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:1666-1674, 2024
Classification models based on deep neural networks (DNNs) must be calibrated to measure the reliability of predictions. Some recent calibration methods have employed a probabilistic model on the probability simplex. However, these calibration method
Externí odkaz:
http://arxiv.org/abs/2402.13765
The generalization ability of Deep Neural Networks (DNNs) is still not fully understood, despite numerous theoretical and empirical analyses. Recently, Allen-Zhu & Li (2023) introduced the concept of multi-views to explain the generalization ability
Externí odkaz:
http://arxiv.org/abs/2402.01095
Autor:
Kutsuna, Takuro
Distribution shifts are problems where the distribution of data changes between training and testing, which can significantly degrade the performance of a model deployed in the real world. Recent studies suggest that one reason for the degradation is
Externí odkaz:
http://arxiv.org/abs/2304.03440
One major challenge in machine learning applications is coping with mismatches between the datasets used in the development and those obtained in real-world applications. These mismatches may lead to inaccurate predictions and errors, resulting in po
Externí odkaz:
http://arxiv.org/abs/2303.05102
Multiple sequences alignment (MSA) is a traditional and challenging task for time-series analyses. The MSA problem is formulated as a discrete optimization problem and is typically solved by dynamic programming. However, the computational complexity
Externí odkaz:
http://arxiv.org/abs/2006.15753
Autor:
Kutsuna, Takuro
0048
甲第19335号
情博第587号
新制||情||102(附属図書館)
32337
学位規則第4条第1項該当
Doctor of Informatics
Kyoto University
DFAM
甲第19335号
情博第587号
新制||情||102(附属図書館)
32337
学位規則第4条第1項該当
Doctor of Informatics
Kyoto University
DFAM
Externí odkaz:
http://hdl.handle.net/2433/202740
Autor:
Kutsuna, Takuro1, Yamamoto, Akihiro2
Publikováno v:
Intelligent Data Analysis. 2014, Vol. 18 Issue 5, p889-910. 22p.
