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

► Levenberg-Marquardt (L-M) and Boyden, Fletcher, Goldfarb and Shanno (BFGS) update Quasi-Newton (Q-N)-based BPNN networks are equally efficient as adaptive learning (A-L) algorithm-based BPNN network. ► L-M algorithm has fastest network convergence rate, followed by BFGS update Q-N and A-L algorithm. ► A-L -based BPNN learns faster than BFGS update Q-N, and L-M takes maximum time for network training. ► A-L algorithm is relatively easy-to-understand and implement, as compared to L-M or BFGS update Q-N algorithm, for online process control.