Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Tomonari Masada"'
Autor:
Toru Sasaki, Tomonari Masada
Publikováno v:
2022 IEEE International Conference on Data Mining Workshops (ICDMW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee73a1c59548c53f563f6960a28c706f
https://doi.org/10.1109/icdmw58026.2022.00045
https://doi.org/10.1109/icdmw58026.2022.00045
Autor:
Tomonari Masada
Publikováno v:
Information Management and Big Data ISBN: 9783031044465
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0995e0093df18cf1bd67e7747f67d966
https://doi.org/10.1007/978-3-031-04447-2_19
https://doi.org/10.1007/978-3-031-04447-2_19
Publikováno v:
2020 International Symposium on Semiconductor Manufacturing (ISSM).
In semiconductor manufacturing processes, it is important to quickly identify any signs of the occurrence of defects. We applied a time-series clustering method to the signal data of processing equipment and obtained information related to the occurr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::307b60633f79584dae55446202e7b451
https://doi.org/10.1109/issm51728.2020.9377525
https://doi.org/10.1109/issm51728.2020.9377525
Autor:
Yuzana Win, Tomonari Masada
Publikováno v:
ICTC
Myanmar is one of the developing countries situated in South-East Asia, and there are still many areas that have been under-developed with respect to advanced natural language processing technologies, where text-to-speech is one of them. The main mot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e81953be6949c6835e79cc84c0db05c3
https://doi.org/10.1109/ictc49870.2020.9289599
https://doi.org/10.1109/ictc49870.2020.9289599
Publikováno v:
ICTC
The main motivation of this paper is to improve the naturalness of Myanmar text-to-speech system using an end-to-end generative model called Tacotron. We introduce the open-source implementation for Myanmar text-to-speech system with very high natura
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ab42f13a9f37875bffab073528f79045
https://doi.org/10.1109/ictc49870.2020.9289277
https://doi.org/10.1109/ictc49870.2020.9289277
Autor:
Tomonari Masada
Publikováno v:
Current Trends in Web Engineering ISBN: 9783030512521
ICWE Workshops
ICWE Workshops
This paper proposes a new variational autoencoder (VAE) for topic models. The variational inference (VI) for Bayesian models approximates the true posterior distribution by maximizing a lower bound of the log marginal likelihood of observations. We c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61bc92f49b7230e95120b0586783e1f2
https://doi.org/10.1007/978-3-030-51253-8_6
https://doi.org/10.1007/978-3-030-51253-8_6
Publikováno v:
ICDM Workshops
We propose a novel method to use the topics obtained by topic modeling for sensor data analysis. This paper describes a case study where we perform an exploratory data analysis of manufacturing sensor data by using latent Dirichlet allocation (LDA) a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd8a847c79a9fbfa9005a99ac847cbde
https://doi.org/10.1109/icdmw.2019.00064
https://doi.org/10.1109/icdmw.2019.00064
Autor:
Tomonari Masada
Publikováno v:
ICDPA
This paper proposes a Bayesian probabilistic document model whose variational inference is achieved by using an implicit approximate posterior distribution. The proposed model generates a set of documents as follows. First, we draw a noise vector fro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::47bf53e791f01ff20918c70ef623cf23
https://doi.org/10.1145/3224207.3224214
https://doi.org/10.1145/3224207.3224214
Autor:
Tomonari Masada, Atsuhiro Takasu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319937120
ICCS (3)
ICCS (3)
This paper proposes a method of scoring sequences generated by recurrent neural network (RNN) for automatic Tanka composition. Our method gives sequences a score based on topic assignments provided by latent Dirichlet allocation (LDA). When many word
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a1b64daf747e897cc935787f0c6124a1
https://doi.org/10.1007/978-3-319-93713-7_33
https://doi.org/10.1007/978-3-319-93713-7_33
Autor:
Tomonari Masada, Atsuhiro Takasu
Publikováno v:
Advanced Data Mining and Applications ISBN: 9783030050894
ADMA
ADMA
This paper proposes adversarial learning for topic models. Adversarial learning we consider here is a method of density ratio estimation using a neural network called discriminator. In generative adversarial networks (GANs) we train discriminator for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a60d4665cf20263e4e6b9854716d6d3e
https://doi.org/10.1007/978-3-030-05090-0_25
https://doi.org/10.1007/978-3-030-05090-0_25