Optimizing number of hidden neurons in neural networks

In this paper, a novel and effective criterion based on the estimation of the signal-to-noise-ratio figure (SNRF) is proposed to optimize the number of hidden neurons in neural networks to avoid overfitting in the function approximation. SNRF can quantitatively measure the useful information left unlearned so that overfitting can be automatically detected from the training error only without use of a separate validation set. It is illustrated by optimizing the number of hidden neurons in a multi-layer perceptron (MLP) using benchmark datasets. The criterion can be further utilized in the optimization of other parameters of neural networks when overfitting needs to be considered. KEY WORDS Neural network, network optimization, function approximation, overfitting, signal-to-noise ratio figure

• Type: Conference
• Year: 2007
• Where: AIA
• Authors: Yue Liu, Janusz A. Starzyk, Zhen Zhu
• Keywords: AIA 2007, Artificial Intelligence, Function Approximation, Hidden Neurons, Neural Network