Temporal Overdrive Recurrent Neural Network
This work addresses a domain-specific challenge in system identification for time series analysis, but it appears incremental as it builds on existing recurrent architectures with preliminary results.
The authors tackled the problem of modeling systems with multiple characteristic timescales by proposing a novel recurrent neural network architecture with separate neuron groups for each timescale, showing promising preliminary results on synthetic data in time series prediction tasks.
In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics. The proposed network is composed by several recurrent groups of neurons that are trained to separately adapt to each timescale, in order to improve the system identification process. We test our framework on time series prediction tasks and we show some promising, preliminary results achieved on synthetic data. To evaluate the capabilities of our network, we compare the performance with several state-of-the-art recurrent architectures.