Deep Belief Network Using Reinforcement Learning and Its Applications to Time Series Forecasting

Takaomi Hirata, Takashi Kuremoto, Masanao Obayashi, Shingo Mabu, Kunikazu Kobayashi

Abstract: Artificial neural networks (ANNs) typified by deep learning (DL) is one of the artificial intelligence technology which is attracting the most attention of researchers recently. However, the learning algorithm used in DL is usually with the famous error-backpropagation (BP) method. In this paper, we adopt a reinforcement learning (RL) algorithm “Stochastic Gradient Ascent (SGA)” proposed by Kimura and Kobayashi into a Deep Belief Net (DBN) with multiple restricted Boltzmann machines (RBMs) instead of BP learning method. A long-term prediction experiment, which used a benchmark of time series forecasting competition, was performed to verify the effectiveness of the proposed method.