PROJECT TITLE :
Fast learning algorithm to improve performance of Quickprop
Quickprop is one in all the foremost popular fast learning algorithms in coaching feed-forward neural networks. Its learning rate is fast; but, it's still limited by the gradient of the backpropagation algorithm and it's easily trapped into a local minimum. Proposed is a new quick learning algorithm to beat these two drawbacks. The performance investigation in several learning issues (applications) shows that the new algorithm perpetually converges with a faster learning rate compared with Quickprop and alternative fast learning algorithms. The improvement in international convergence capability is especially giant, that increased from 4 to a hundred% in one learning downside.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here