Hybrid learning algorithm for Gaussian potential function networks

Chen, C.-L.; Chen, W.-C.; Chang, Fi‐John

doi:10.1049/ip-d.1993.0058

Cited by 35 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2). As can be seen, the proposed model is a hybrid of Chen et al (1993) (feedback with a filter in each neuron) and Ciocoiu (1996) (using filters as synaptic connections); the main contribution of this paper is the generalisation of the model to systems with any number of inputs and two outputs and the practical application thereof. With a system of two inputs (x 1 (k), x 2 (k)) and two outputs (y O1 (k), y O2 (k)), the model of the radial basis functions is:…”

Section: Neural Modelmentioning

confidence: 99%

“…RBF networks were initially developed for the interpolation of data in multidimensional spaces. The advantages of these networks are their simplicity and their trainability by means of easy to implement algorithms with a high convergence speed, as there is a linear relationship between the parameters to be adjusted (synaptic connections) and the neural network output (Chen et al, 1993).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Control of a Robotic Wheelchair Using Recurrent Networks

et al. 2005

View full text Add to dashboard Cite

This paper describes an adaptive neural control system for governing the movements of a robotic wheelchair. It presents a new model of recurrent neural network based on a RBF architecture and combining in its architecture local recurrence and synaptic connections with FIR filters. This model is used in two different control architectures to command the movements of a robotic wheelchair. The training equations and the stability conditions of the control system are obtained. Practical tests show that the results achieved using the proposed method are better than those obtained using PID controllers or other recurrent neural networks models

show abstract

Section: Neural Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Control of a Robotic Wheelchair Using Recurrent Networks

et al. 2005

View full text Add to dashboard Cite

show abstract

“…Equation (4) checks whether the network met the required sum squared error specification for the past M outputs of the network. Equation (5) ensures that the new node to be added is sufficiently far from all the existing nodes.…”

Section: Minimal Resource Allocating Network (Mran) Algorithmmentioning

confidence: 99%

“…These gaussian functions have two parameters namely the center and width which have to be determined. Number of algorithms have been proposed for training the RBF network [5] [6] [7]. The classical approach to RBF implementation is to fix the number of hidden neurons a priori along with its centers and widths, based on some properties of the input data, and then estimate the weights connecting the hidden and output neurons.…”

Section: Introductionmentioning

confidence: 99%

Analysis of minimal radial basis function network algorithm for real-time identification of nonlinear dynamic systems

Li¹,

Sundararajan²,

Saratchandran³

2000

IEE Proceedings - Control Theory and Applications

View full text Add to dashboard Cite

This paper presents first a performance analysis of the recently developed Minimal Resource Allocating Network (MRAN) algorithm for on-line identification of nonlinear dynamic systems. Using nonlinear time invariant and time varying identification benchmark problems, MRAN's performance is compared with the recently proposed On-line Structural Adaptive Hybrid Learning (ONSAHL) algorithm of Junge and Unbehauen. The results indicate that MRAN realizes networks using fewer hidden neurons than ONSAHL algorithm with better approximation accuracy. Next, methods for improving the run time performance of MRAN for real time identification of the nonlinear systems are developed. An extension to MRAN referred to as the Extended Minimum Resource Allocating Network (EMRAN) which utilizes a winner neuron strategy is highlighted. This modification reduces the computation load for MRAN and leads to considerable reduction in the learning time with only a slight increase in the approximation error. Using the same benchmark problems, the results show that EMRAN is well suited for fast on-line identification of nonlinear plants.

show abstract

Radial Basis Function Networks

Du¹,

Swamy

2013

Neural Networks and Statistical Learning

View full text Add to dashboard Cite

Hybrid learning algorithm for Gaussian potential function networks

Cited by 35 publications

References 1 publication

Control of a Robotic Wheelchair Using Recurrent Networks

Control of a Robotic Wheelchair Using Recurrent Networks

Analysis of minimal radial basis function network algorithm for real-time identification of nonlinear dynamic systems

Radial Basis Function Networks

Contact Info

Product

Resources

About