Abstract
Recently, echo state network (ESN) has attracted a great deal of attention due to its high accuracy and efficient learning performance. Compared with the traditional random structure and classical sigmoid units, simple circle topology and leaky integrator neurons have more advantages on reservoir computing of ESN. In this paper, we propose a new model of ESN with both circle reservoir structure and leaky integrator units. By comparing the prediction capability on Mackey-Glass chaotic time series of four ESN models: classical ESN, circle ESN, traditional leaky integrator ESN, circle leaky integrator ESN, we find that our circle leaky integrator ESN shows significantly better performance than other ESNs with roughly 2 orders of magnitude reduction of the predictive error. Moreover, this model has stronger ability to approximate nonlinear dynamics and resist noise than conventional ESN and ESN with only simple circle structure or leaky integrator neurons. Our results show that the combination of circle topology and leaky integrator neurons can remarkably increase dynamical diversity and meanwhile decrease the correlation of reservoir states, which contribute to the significant improvement of computational performance of Echo state network on time series prediction.
Highlights
Echo state network (ESN), one of the improved recurrent neural networks, has attracted extensive attention since proposed by Jaeger in 2002 [1]
This work provides an efficient model of ESN with excellent performance and simple network structure, which is very meaningful for the broad application of ESN on various fields
A new ESN model based on circle topology and leaky integrator units is proposed
Summary
Echo state network (ESN), one of the improved recurrent neural networks, has attracted extensive attention since proposed by Jaeger in 2002 [1]. We introduce two ESNs with the simple circle reservoir topology shown in Fig 2 with sigmoid or leaky integrator neurons, which are called circle ESN (C-ESN) and circle LI-ESN (C-LI-ESN) respectively.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.