Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process.
Indrajit MukherjeeSrikanta RoutroyPublished in: Expert Syst. Appl. (2012)
Keyphrases
- levenberg marquardt
- neural network
- back propagation
- artificial neural networks
- cost function
- least squares
- objective function
- training algorithm
- genetic algorithm
- learning algorithm
- simulated annealing
- bundle adjustment
- optimization algorithm
- optimal solution
- support vector machine svm
- fault diagnosis
- convergence rate
- semi supervised
- image sequences
- neural network training
- quasi newton