Convergence of Online Gradient Method with a Penalty Term for Feedforward Neural Networks with Stochastic
نویسندگان
چکیده
Abstract Online gradient algorithm has been widely used as a learning algorithm for feedforward neural network training. In this paper, we prove a weak convergence theorem of an online gradient algorithm with a penalty term, assuming that the training examples are input in a stochastic way. The monotonicity of the error function in the iteration and the boundedness of the weight are both guaranteed. We also present a numerical experiment to support our results.
منابع مشابه
Convergence of an Online Gradient Algorithm with Penalty for Two-layer Neural Networks
Online gradient algorithm has been widely used as a learning algorithm for feedforward neural networks training. Penalty is a common and popular method for improving the generalization performance of networks. In this paper, a convergence theorem is proved for the online gradient learning algorithm with penalty, a term proportional to the magnitude of the weights. The monotonicity of the error ...
متن کاملBoundedness of a Batch Gradient Method with Penalty for Feedforward Neural Networks
This paper considers a batch gradient method with penalty for training feedforward neural networks. The role of the penalty term is to control the magnitude of the weights and to improve the generalization performance of the network. An usual penalty is considered, which is a term proportional to the norm of the weights. The boundedness of the weights of the network is proved. The boundedness i...
متن کاملConvergence of online gradient method for feedforward neural networks with smoothing L1/2 regularization penalty
Minimization of the training regularization term has been recognized as an important objective for sparse modeling and generalization in feedforward neural networks. Most of the studies so far have been focused on the popular L2 regularization penalty. In this paper, we consider the convergence of online gradient method with smoothing L1/2 regularization term. For normal L1/2 regularization, th...
متن کاملTraining Pi-Sigma Network by Online Gradient Algorithm with Penalty for Small Weight Update
A pi-sigma network is a class of feedforward neural networks with product units in the output layer. An online gradient algorithm is the simplest and most often used training method for feedforward neural networks. But there arises a problem when the online gradient algorithm is used for pi-sigma networks in that the update increment of the weights may become very small, especially early in tra...
متن کاملConvergence Analysis of Multilayer Feedforward Networks Trained with Penalty Terms: a Review
Gradient descent method is one of the popular methods to train feedforward neural networks. Batch and incremental modes are the two most common methods to practically implement the gradient-based training for such networks. Furthermore, since generalization is an important property and quality criterion of a trained network, pruning algorithms with the addition of regularization terms have been...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005