TY - JOUR
T1 - Convergence of Gradient Method for Double Parallel Feedforward Neural Network
AU - J. Wang, W. Wu, Z. Li & L. Li
JO - International Journal of Numerical Analysis and Modeling
VL - 3
SP - 484
EP - 495
PY - 2011
DA - 2011/08
SN - 8
DO - http://doi.org/
UR - https://global-sci.org/intro/article_detail/ijnam/697.html
KW - Double parallel feedforward neural network, gradient method, monotonicity, convergence.
AB - <p style="text-align: justify;">The deterministic convergence for a Double Parallel Feedforward
Neural Network (DPFNN) is studied. DPFNN is a parallel connection of a
multi-layer feedforward neural network and a single layer feedforward neural
network. Gradient method is used for training DPFNN with finite training
sample set. The monotonicity of the error function in the training iteration
is proved. Then, some weak and strong convergence results are obtained, indicating
that the gradient of the error function tends to zero and the weight
sequence goes to a fixed point, respectively. Numerical examples are provided,
which support our theoretical findings and demonstrate that DPFNN has faster
convergence speed and better generalization capability than the common feedforward
neural network.</p>