2.2k citations
- Keio UniversityJP22 papers
- The University of TokyoJP16 papers
- IBM (United States)US14 papers
- IBM Research - Thomas J. Watson Research CenterUS12 papers
- Kyoto UniversityJP10 papers
- IBM Research - ZurichCH8 papers
- IBM Research - AlmadenUS7 papers
- Mitsubishi UFJ Financial Group, Inc. (Japan)JP6 papers
- Mizuho Research & Technologies, Ltd. (Japan)JP6 papers
- Mizuho (Japan)JP5 papers
- Osaka Prefecture UniversityJP5 papers
- Mitsubishi Chemical (Japan)JP4 papers
6 papers · 1 filter
Time-Discounting Convolution for Event Sequences with Ambiguous Timestamps
Takayuki Katsuki, Takayuki Osogami, Akira Koseki +4
This paper proposes a method for modeling event sequences with ambiguous timestamps, a time-discounting convolution. Unlike in ordinary time series, time intervals are not constant…
Reinforcement Learning Testbed for Power-Consumption Optimization
Takao Moriyama, Giovanni De Magistris, Michiaki Tatsubori +3
Common approaches to control a data-center cooling system rely on approximated system/environment models that are built upon the knowledge of mechanical cooling and electrical and…
Recent Advances in Physical Reservoir Computing: A Review
Gouhei Tanaka, Toshiyuki Yamane, Jean Benoit Héroux +6
Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state ne…
Focusing on What is Relevant: Time-Series Learning and Understanding using Attention
Phongtharin Vinayavekhin, Subhajit Chaudhury, Asim Munawar +4
This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of…
Internal Model from Observations for Reward Shaping
Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana +1
Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functi…
Supervising Unsupervised Learning with Evolutionary Algorithm in Deep Neural Network
Takeshi Inagaki
A method to control results of gradient descent unsupervised learning in a deep neural network by using evolutionary algorithm is proposed. To process crossover of unsupervisedly t…