Convergence of an Online Gradient Algorithm with Penalty for Two-layer Neural Networks
نویسندگان
چکیده
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 function with such a penalty term is guaranteed during the training iteration. A key point of the proofs is the boundedness of the network weights, which is also a desired rewarding of adding penalty. Key–Words: Convergence, Online gradient algorithm, Feedforward neural network, Penalty, Boundedness, Monotonicity
منابع مشابه
Convergence of Online Gradient Method with a Penalty Term for Feedforward Neural Networks with Stochastic
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 guaran...
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 کاملClassification of ECG signals using Hermite functions and MLP neural networks
Classification of heart arrhythmia is an important step in developing devices for monitoring the health of individuals. This paper proposes a three module system for classification of electrocardiogram (ECG) beats. These modules are: denoising module, feature extraction module and a classification module. In the first module the stationary wavelet transform (SWF) is used for noise reduction of ...
متن کاملA Higher Order Online Lyapunov-Based Emotional Learning for Rough-Neural Identifiers
o enhance the performances of rough-neural networks (R-NNs) in the system identification, on the base of emotional learning, a new stable learning algorithm is developed for them. This algorithm facilitates the error convergence by increasing the memory depth of R-NNs. To this end, an emotional signal as a linear combination of identification error and its differences is used to achie...
متن کاملConvergence of Online Gradient Method for Pi-sigma Neural Networks with Inner-penalty Terms
This paper investigates an online gradient method with innerpenalty for a novel feed forward network it is called pi-sigma network. This network utilizes product cells as the output units to indirectly incorporate the capabilities of higherorder networks while using a fewer number of weights and processing units. Penalty term methods have been widely used to improve the generalization performan...
متن کامل