AIM: Trains FFNN using different algrithms and compares their performance
INPUT: Set the no. of hidden layers in FFNN Set the Algorithm parameters
OUTPUT: The error convergence can be plotted using plot(err_) Trained NNs are saved in NN_ Output of NNs for all patterns can be tested using test(NN_,data)
PUBLICATION CITATION: If you're using this code, please cite our paper: @inproceedings{arora2017hjb, title={HJB equation based learning scheme for neural networks}, author={Arora, Vipul and Behera, Laxmidhar and Reddy, Tharun Kumar and Yadav, Ajay Pratap}, booktitle={Neural Networks (IJCNN), 2017 International Joint Conference on}, pages={2298--2305}, year={2017}, organization={IEEE} }IJCNN2017