Deep Neural Networks for Time Series Analytics

[19] Song Q, Chissom BS. Fuzzy time series and its models. Fuzzy Sets and

Time Series Analysis - Data, Methods, and Applications

[20] Song Q, Chissom BS. Forecasting enrollment with fuzzy time series—Part II. Fuzzy Sets and Systems. 1994;62:1-8

[21] Song Q, Leland RP, Chissom BS. Fuzzy stochastic time series and its models. Fuzzy Sets and Systems. 1997;

[22] Teoh HJ, Chen CH, Chu HH, Chen JS. Fuzzy time series model based on probabilistic approach and rough set rule induction for empirical research in stock markets. Data & Knowledge Engineering. 2008;67:103-117

[23] Taiwan Stock Exchange Corporation [Internet]. 2018. Available from: http:// www.twse.com.tw/en/ [Accessed:

Systems. 1993;54:269-277

88:333-341

August 03, 2018]

36

Chapter 3

Abstract

1. Introduction

39

Training Deep Neural Networks

with Reinforcement Learning for

Takashi Kuremoto,Takaomi Hirata, Masanao Obayashi,

As a kind of efficient nonlinear function approximators, artificial neural networks (ANN) have been popularly applied to time series forecasting. The training method of ANN usually utilizes error back-propagation (BP) which is a supervised learning algorithm proposed by Rumelhart et al. in 1986; meanwhile, authors proposed to improve the robustness of the ANN for unknown time series prediction using a reinforcement learning algorithm named stochastic gradient ascent (SGA) originally proposed by Kimura and Kobayashi for control problems in 1998. We also successfully use a deep belief net (DBN) stacked by multiple restricted Boltzmann machines (RBMs) to realized time series forecasting in 2012. In this chapter, a stateof-the-art time series forecasting system that combines RBMs and multilayer perceptron (MLP) and uses SGA training algorithm is introduced. Experiment results showed the high prediction precision of the novel system not only for

Keywords: artificial neural networks (ANN), deep learning (DL), reinforcement learning (RL), deep belief net (DBN), restricted Boltzmann machine (RBM),

Artificial neural networks (ANN), which are mathematical models for function approximation, classification, pattern recognition, nonlinear control, etc., have been successfully applied in the field of time series analysis and forecasting instead of linear models such as 1970s ARIMA [1] since 1980s [2–7]. In [2], Casdagli used a radial basis function network (RBFN) which is a kind of feed-forward neural network with Gaussian hidden units to predict chaotic time series data, such as the Mackey-Glass, the Ikeda map, and the Lorenz chaos in 1989. In [3, 4], Lendasse et al. organized a time series forecasting competition for neural network prediction methods with a five-block artificial time series data named CATS since 2004. The goal of CATS competition was to predict 100 missing values of the time series data in five sets which included 980 known values and 20 successive unknown values in each set (details are in Section 3.1). There were 24 submissions to the competition, and five kinds of methods were selected by the IJCNN2004: filtering techniques including Bayesian methods, Kalman filters, and so on; recurrent neural networks

Time Series Forecasting

Shingo Mabu and Kunikazu Kobayashi

benchmark data but also for real phenomenon time series data.

multilayer perceptron (MLP), stochastic gradient ascent (SGA)
