Forecasting Real Time Series Data using Deep Belief Net and Reinforcement Learning
- 10.2991/jrnal.2018.4.4.1How to use a DOI?
- deep learning, restricted Boltzmann machine, stochastic gradient ascent, reinforcement learning, error-backpropagation
Hinton’s deep auto-encoder (DAE) with multiple restricted Boltzmann machines (RBMs) is trained by the unsupervised learning of RBMs and fine-tuned by the supervised learning with error-backpropagation (BP). Kuremoto et al. proposed a deep belief network (DBN) with RBMs as a time series predictor, and used the same training methods as DAE. Recently, Hirata et al. proposed to fine-tune the DBN with a reinforcement learning (RL) algorithm named “Stochastic Gradient Ascent (SGA)” proposed by Kimura & Kobayashi and showed the priority to the conventional training method by a benchmark time series data CATS. In this paper, DBN with SGA is invested its effectiveness for real time series data. Experiments using atmospheric CO2 concentration, sunspot number, and Darwin sea level pressures were reported.
- © 2018, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - JOUR AU - Takaomi Hirata AU - Takashi Kuremoto AU - Masanao Obayashi AU - Shingo Mabu AU - Kunikazu Kobayashi PY - 2018 DA - 2018/03/31 TI - Forecasting Real Time Series Data using Deep Belief Net and Reinforcement Learning JO - Journal of Robotics, Networking and Artificial Life SP - 260 EP - 264 VL - 4 IS - 4 SN - 2352-6386 UR - https://doi.org/10.2991/jrnal.2018.4.4.1 DO - 10.2991/jrnal.2018.4.4.1 ID - Hirata2018 ER -