A robust parameters self-tuning learning algorithm for multilayer feedforward neural network

In this paper, a new and efficient adaptive-learning algorithm for multilayer feedforward neural networks is proposed. The main characteristic of this new algorithm is that learning parameters such as learning rate ( η ) and momentum ( α ) can be automatically adjusted according to the learning trajectory. Originally, the proposed algorithm was inspired by the use of the 1st order Taylor series expansion to approximate Δ E null P , the variation...