Time Series Prediction
We propose a dual-stage attention based recurrent neural network (DA-RNN) to address for time series prediction. In the first stage, we introduce an input attention mechanism to adaptively extract relevant driving series (a.k.a., input features) at each timestamp by referring to the previous encoder hidden state. In the second stage, we use a temporal attention mechanism to select relevant encoder hidden states across all the timestamps. With this dual-stage attention scheme, our model can not only make prediction effectively, but can also be easily interpreted. Thorough empirical studies based upon the SML 2010 dataset and the NASDAQ 100 Stock dataset demonstrate that DA-RNN can outperform state-of-the-art methods for time series prediction.
Cellular Automata is a dynamic system with simple construction but complex self-organizing behaviour. The model consists of a lattice of cells with discrete states, which evolve in discrete time steps according to definite rules. Each cell's next state will be determined by its current state and the states of its nearest neighbors. In this paper, we introduce Cellular Automata as a propagation mechanism to intuitively detect the salient object. It’s surprising to find out that parallel evolution can improve all the existing methods to a similar level regardless of their o- riginal results. In addition, considering that some effective algorithms have been proposed in the Bayesian framework, we also combine Cellular Automata with Bayesian theory to integrate multiple saliency maps. Extensive experiments on six public datasets demonstrate that the proposed algorithm outperforms state-of-the-art methods.