A general backpropagation algorithm for feedforward neural networks learning

IEEE Transactions on Neural Networks

Volumn 13, Issue 1, 2002, Pages 251-254

  Yu, Xinghuo ^a   Efe, M Onder ^b   Kaynak, Okyay ^c  

^a CENTRAL QUEENSLAND UNIVERSITY   (Australia)

^b CARNEGIE MELLON UNIVERSITY   (United States)

^c BOGAZICI UNIVERSITY   (Turkey)

Author keywords

Backpropagation; Feedforward neural networks; Stability; Training

Indexed keywords

BACKPROPAGATION; CONVERGENCE OF NUMERICAL METHODS; ERROR ANALYSIS; FEEDFORWARD NEURAL NETWORKS; LYAPUNOV METHODS; SYSTEM STABILITY; TIME VARYING NETWORKS;

BACKPROPAGATION ALGORITHMS; ERROR FUNCTION; NEURAL NETWORK TRAINING ALGORITHM; TIME VARYING INPUTS;

LEARNING ALGORITHMS;

EID: 0036129263     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.977323     Document Type: Letter

References (12)

1. On-line neural network learning algorithm with exponential convergence rate
2. Advanced neural network training algorithm with reduced complexity based on Jacobian deficiency
3. A generalized learning paradigm exploiting the structure of feedforward neural networks
4. Training feedforward neural networks with the Marquardt algorithm
5. A simplification of the backpropagation through time algorithm for optimal neurocontroller
6. Stabilization with relaxed controls
7. Absolute exponential stability of neural networks with a general class of activation functions
8. On equilibra, stability, and instability of Hopfield neural networks