Hierarchical Temporal Representation in Linear Reservoir Computing
This work offers incremental insights into deep learning in the temporal domain for researchers in reservoir computing and recurrent neural networks.
The paper tackled the problem of understanding hierarchical temporal representation in deep recurrent neural networks by analyzing linear reservoir computing units on Multiple Superimposed Oscillator tasks, providing evidence through frequency analysis of state signals.
Recently, studies on deep Reservoir Computing (RC) highlighted the role of layering in deep recurrent neural networks (RNNs). In this paper, the use of linear recurrent units allows us to bring more evidence on the intrinsic hierarchical temporal representation in deep RNNs through frequency analysis applied to the state signals. The potentiality of our approach is assessed on the class of Multiple Superimposed Oscillator tasks. Furthermore, our investigation provides useful insights to open a discussion on the main aspects that characterize the deep learning framework in the temporal domain.