The combination of circle topology and leaky integrator neurons remarkably improves the performance of echo state network on time series prediction
نویسندگان
چکیده
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.
منابع مشابه
Wireless Spectral Prediction by the Modified Echo State Network Based on Leaky Integrate and Fire Neurons
With the rapid development of wireless communication technology, the wireless spectrum resources are dwindling. Cognitive radio (CR) is the key technology to solve this problem. In view of the echo state network advantages compared to traditional recursive neural network, we construct the new neural network, echo state network based on leaky integrate and fire neurons (LIF_ESN), and prove that ...
متن کاملOptimization and applications of echo state networks with leaky- integrator neurons
Standard echo state networks (ESNs) are built from simple additive units with a sigmoid activation function. Here we investigate ESNs whose reservoir units are leaky integrator units. Units of this type have individual state dynamics, which can be exploited in various ways to accommodate the network to the temporal characteristics of a learning task. We present stability conditions, introduce a...
متن کاملState Noise Effects on the Stochastic Gradient Descent Optimization Method for Echo State Networks with Leaky Integrator Neurons
Executive Summary Echo state networks (ESNs) are a novel approach to modeling the nonlinear dynamical systems that abound in the sciences and engineering. They employ artificial recurrent neural networks in a way that has been independently proposed as a learning mechanism in biological brains and lead to a fast and simple algorithm for supervised training. ESNs are controlled by several global...
متن کاملAvailability Prediction of the Repairable Equipment using Artificial Neural Network and Time Series Models
In this paper, one of the most important criterion in public services quality named availability is evaluated by using artificial neural network (ANN). In addition, the availability values are predicted for future periods by using exponential weighted moving average (EWMA) scheme and some time series models (TSM) including autoregressive (AR), moving average (MA) and autoregressive moving avera...
متن کاملPerformance Improvement of Expanded Integrated Local Area Networks (RESEARCH NOTE)
In Local Area Networks (LAN) connected together by bridges, flow control and smooth traffic in the network is very important. However, congestion at bridges can cause intensive loss of received frames. In addition, the received frames are thrown away and have to be retransmitted by the source station, which causes more congestion and massive reduction in the overall network throughput. The netw...
متن کامل