Masashi Sugiyama
Overview
Explore the profile of Masashi Sugiyama including associated specialties, affiliations and a list of published articles.
Author names and details appear as published. Due to indexing inconsistencies, multiple individuals may share a name, and a single author may have variations. MedLuna displays this data as publicly available, without modification or verification
Snapshot
Snapshot
Articles
78
Citations
223
Followers
0
Related Specialties
Related Specialties
Top 10 Co-Authors
Top 10 Co-Authors
Published In
Published In
Affiliations
Affiliations
Soon will be listed here.
Recent Articles
1.
Nakamura S, Sugiyama M
Neural Comput
. 2024 Dec;
37(2):294-310.
PMID: 39622008
We study the real-valued combinatorial pure exploration problem in the stochastic multi-armed bandit (R-CPE-MAB). We study the case where the size of the action set is polynomial with respect to...
2.
Zhao T, Li G, Zhao T, Chen Y, Xie N, Niu G, et al.
Neural Netw
. 2024 Sep;
180:106741.
PMID: 39321563
State representations considerably accelerate learning speed and improve data efficiency for deep reinforcement learning (DRL), especially for visual tasks. Task-relevant state representations could focus on features relevant to the task,...
3.
Luo W, Chen S, Liu T, Han B, Niu G, Sugiyama M, et al.
IEEE Trans Pattern Anal Mach Intell
. 2024 Sep;
47(1):305-322.
PMID: 39312440
Real-world data may contain a considerable amount of noisily labeled examples, which usually mislead the training algorithm and result in degraded classification performance on test data. Therefore, Label Noise Learning...
4.
Takahashi S, Sakaguchi Y, Kouno N, Takasawa K, Ishizu K, Akagi Y, et al.
J Med Syst
. 2024 Sep;
48(1):84.
PMID: 39264388
In the rapidly evolving field of medical image analysis utilizing artificial intelligence (AI), the selection of appropriate computational models is critical for accurate diagnosis and patient care. This literature review...
5.
Hasegawa N, Sugiyama M, Igarashi K
Appl Environ Microbiol
. 2024 Jun;
90(7):e0048224.
PMID: 38832775
Importance: Wood-rotting fungi are categorized as either white- or brown-rot modes based on the coloration of decomposed wood. The process of classification can be influenced by human biases. The random...
6.
Zhang J, Song B, Wang H, Han B, Liu T, Liu L, et al.
IEEE Trans Pattern Anal Mach Intell
. 2024 Jan;
46(6):4398-4409.
PMID: 38236681
Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional...
7.
Zhao T, Wu S, Li G, Chen Y, Niu G, Sugiyama M
Neural Comput
. 2023 Jul;
35(10):1657-1677.
PMID: 37523456
Deep reinforcement learning (DRL) provides an agent with an optimal policy so as to maximize the cumulative rewards. The policy defined in DRL mainly depends on the state, historical memory,...
8.
Gao Y, Wu D, Zhang J, Gan G, Xia S, Niu G, et al.
IEEE Trans Neural Netw Learn Syst
. 2023 Jun;
35(10):14878-14888.
PMID: 37314915
Although adversarial training (AT) is regarded as a potential defense against backdoor attacks, AT and its variants have only yielded unsatisfactory results or have even inversely strengthened backdoor attacks. The...
9.
Lv J, Liu B, Feng L, Xu N, Xu M, An B, et al.
IEEE Trans Pattern Anal Mach Intell
. 2023 May;
46(5):2569-2583.
PMID: 37167048
Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL). In PLL, identification-based strategy (IBS) purifies each PL...
10.
Zhao T, Wang Y, Sun W, Chen Y, Niu G, Sugiyama M
Neural Netw
. 2022 Dec;
159:137-152.
PMID: 36566604
Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world...