抄録
Numerous studies on time series prediction have been undertaken by a lot of researchers. Most of them typically used uni-directional computation flow, i.e., present signals are applied to the model as an input and predicted future signals are derived from the model as an output. On the contrary, bi-directional computation style is proposed recently and applied to prediction tasks. A bi-directional neural network model consists of two mutually connected subnetworks and performs direct and inverse transformations bi-directionally. To apply this model to time series prediction tasks, one subnetwork is trained a conventional future prediction task and the other is trained an additional task for past prediction. Since the coupling effects between the future and past prediction subsystems promote the model's signal processing ability, bi-directionalization of the computing architecture makes it possible to improve its performance. Furthermore, in order to investigate the acquired signal transformation, two kinds of chaotic time series, i.e., the Mackey-Glass time series and the “Data Set A”, are adopted in this paper. As a result of computer simulations, it has been found experimentally that the direct and inverse transformations developed independently and their information integration give the bi-directional model an advantage over the uni-directional one.
