An improved asynchronous batch gradient method for ridge polynomial neural network

Abstract

The ridge polynomial neural network composed of pi-sigma modules is a typical higher-order feedforward network, which has good non-linear mapping capabilities. Due to the strong coupling of the network structure, the synchronous gradient method can easily result in significant fluctuations in updated weights. This will reduce the generalization ability of the ridge polynomial neural network for solving classification problems. In this paper, the proposed method is a novel improved asynchronous batch gradient method, and combined with the adaptive parameters of the activation function are trained synchronously. We strictly prove the convergence theorem of the improved method. The numerical experimental results also indicate that our method for training ridge polynomial neural networks can help the weight changes smoothly and the network has good generalization ability. The feasibility and effectiveness of our method are verified from both theoretical and experimental perspectives.