Deterministic convergence of conjugate gradient method for feedforward neural networks

@article{Wang2011DeterministicCO,
  title={Deterministic convergence of conjugate gradient method for feedforward neural networks},
  author={Jian Wang and Wei Wu and Jacek M. Zurada},
  journal={Neurocomputing},
  year={2011},
  volume={74},
  pages={2368-2376}
}
Conjugate gradient methods have many advantages in real numerical experiments, such as fast convergence and low memory requirements. This paper considers a class of conjugate gradient learning methods for backpropagation (BP) neural networks with three layers. We propose a new learning algorithm for almost cyclic BP neural networks based on PRP conjugate gradient method. We then establish the deterministic convergence properties for three different learning fashions, i.e., batch mode, cyclic… CONTINUE READING