The importance of an adaptive gain variation method in back-propagation neural network learning algorithms
نویسندگان
چکیده
In a 'feed forward' algorithm, the slope of the activation function is directly influenced by a parameter referred to as 'gain'. In this paper, the influence of the variation of 'gain' on the learning ability of a neural network is analysed. Multi layer feed forward neural networks have been assessed. Physical interpretation of the relationship between the gain value and learning rate and weight values is given. Instead of a constant 'gain' value, we propose an algorithm to change the gain value adaptively for each node. The efficacy of the proposed method is verified by means of simulation on a function approximation problem using sequential mode of training. The results show that the proposed method considerably improves the learning speed of the general back-propagation algorithm.
منابع مشابه
An Optimal Utilization of Cloud Resources using Adaptive Back Propagation Neural Network and Multi-Level Priority Queue Scheduling
With the innovation of cloud computing industry lots of services were provided based on different deployment criteria. Nowadays everyone tries to remain connected and demand maximum utilization of resources with minimum timeand effort. Thus, making it an important challenge in cloud computing for optimum utilization of resources. To overcome this issue, many techniques have been proposed ...
متن کاملOn the use of back propagation and radial basis function neural networks in surface roughness prediction
Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically, feed-forward artificial neural networks are trained with three different back propagation algorithms, ...
متن کاملThe Effect of Gain Variation in Improving Learning Speed of Back Propagation Neural Network Algorithm on Classification Problems
We proposed a method for improving the performance of the back propagation algorithm by introducing the adaptive gain of the activation function. In a ‘feed forward’ algorithm, the slope of the activation function is directly influenced by a parameter referred to as ‘gain’. In this paper, the influence of the adaptive gain on the learning ability of a neural network is analysed. Multi layer fee...
متن کاملAdaptive Quaternion Attitude Control of Aerodynamic Flight Control Vehicles
Conventional quaternion based methods have been extensively employed for spacecraft attitude control where the aerodynamic forces can be neglected. In the presence of aerodynamic forces, the flight attitude control is more complicated due to aerodynamic moments and inertia uncertainties. In this paper, a robust nero-adaptive quat...
متن کاملDesign of an Adaptive-Neural Network Attitude Controller of a Satellite using Reaction Wheels
In this paper, an adaptive attitude control algorithm is developed based on neural network for a satellite using four reaction wheels in a tetrahedron configuration. Then, an attitude control based on feedback linearization control is designed and uncertainties in the moment of inertia matrix and disturbances torque have been considered. In order to eliminate the effect of these uncertainties, ...
متن کامل