This report is an introduction to Artificial Neural Networks. The various aspects of neural networks are explained, demonstrated and the applications of neural networks are described.
Neural networks have been used to model the nonlinear characteristics of memory less nonlinear channels using the backpropagation learning (BP) with experimental training data. Backpropagation is a supervised learning algorithm and is mainly used by Multi-Layer-Perceptrons to change the weights connected to the net's hidden neuron layer(s).
Backpropagation is a supervised learning algorithm and is mainly used by Multi-Layer-Perceptrons to change the weights connected to the net's hidden neuron layer(s). The mean transient and convergence behavior of a simplified two-layer neural network has been studied previously in order to better understand this neural network application. The network was trained with zero mean Gaussian data. This paper extends these results to include the effects of the weight fluctuations on the mean square error (MSE).
The backpropagation algorithm uses a computed output error to change the weight values in backward direction. To get this net error, a forwardpropagation phase must have been done before. While propagating in forward direction, the neurons are being activated using the sigmoid activation function.
The performance analysis is based on the derivation of linear recursions for the variance and covariance of the weights that depend nonlinearly on the mean weights. These linear recursions can be used to predict the local mean-square stability of the weights. The motivation for the development of neural network technology stemmed from the desire to develop an artificial system that could perform "intelligent" tasks similar to those performed by the human brain.
Neural networks have been used to model the nonlinear characteristics of memory less nonlinear channels using the backpropagation learning (BP) with experimental training data. Backpropagation is a supervised learning algorithm and is mainly used by Multi-Layer-Perceptrons to change the weights connected to the net's hidden neuron layer(s).
Backpropagation is a supervised learning algorithm and is mainly used by Multi-Layer-Perceptrons to change the weights connected to the net's hidden neuron layer(s). The mean transient and convergence behavior of a simplified two-layer neural network has been studied previously in order to better understand this neural network application. The network was trained with zero mean Gaussian data. This paper extends these results to include the effects of the weight fluctuations on the mean square error (MSE).
The backpropagation algorithm uses a computed output error to change the weight values in backward direction. To get this net error, a forwardpropagation phase must have been done before. While propagating in forward direction, the neurons are being activated using the sigmoid activation function.The performance analysis is based on the derivation of linear recursions for the variance and covariance of the weights that depend nonlinearly on the mean weights. These linear recursions can be used to predict the local mean-square stability of the weights. The motivation for the development of neural network technology stemmed from the desire to develop an artificial system that could perform "intelligent" tasks similar to those performed by the human brain.
---
(This is the abstract of the Paper Presentation on "Neural Networks - An Insight into Backpropagation" presented by Vinay Kumar @ State level Symposiums in 2004)
---
Copyrighted - Vinay Kumar
No comments:
Post a Comment