Temporal Data Analysis Using Reservoir Computing and Dynamic Memristors

Temporal data analysis is essential in a range of fields from finance to engineering. Recurrent neural networks have gathered much attention since the temporal information captured by the recurrent connections improves the prediction performance. Recently, reservoir computing (RC), which evolves from recurrent neural networks, has been extensively studied for temporal data analysis as it can offer efficient temporal processing of recurrent neural networks with a low training cost. In this thesis, I will present hardware implementation of the RC system using an emerging device – memristor, followed by a theoretical study on hierarchical architectures of the RC system.

A RC hardware system based on dynamic tungsten oxide memristors is demonstrated. Using the memristor-based RC hardware system, high classification accuracy of 99.2% is obtained for spoken digit recognition and autonomous chaotic time series forecasting has been demonstrated over the long term. In the theoretical study, I investigate the influence of the hierarchical reservoir structure on the properties of the reservoir and the performance of the RC system. Analogous to deep neural networks, stacking sub-reservoirs in series is an efficient way to enhance the nonlinearity of data transformation to high-dimensional space and expand the diversity of temporal information captured by the reservoir.

Chair: Professor Wei D. Lu