Backpropagation-based Multi Layer Perceptron Neural Networks

%% Backpropagation for Multi Layer Perceptron Neural Networks %%
% Author: Shujaat Khan, shujaat123@gmail.com
% cite:
% @article{khan2018novel,
% title={A Novel Fractional Gradient-Based Learning Algorithm for Recurrent Neural Networks},
% author={Khan, Shujaat and Ahmad, Jawwad and Naseem, Imran and Moinuddin, Muhammad},
% journal={Circuits, Systems, and Signal Processing},
% volume={37},
% number={2},
% pages={593--612},
% year={2018},
% publisher={Springer US}
% }
%% Description
% In this simulation I used a Golub et al(1999)'s Leukemia Cancer Database.
% The details of the dataset is available online at [1]. The leukemia db
% is a gene expression dataset contains 7128 genes, 2-classes (47-ALL &
% 25-AML), divided into two subsets training and test subsets. The training
% dataset contains 27-ALL, and 11-AML total 38 samples, and the test subset
% contains 20-ALL, and 14-AML total 34 samples.
%
% The genes are ranked using mRMR feature selection method [2] and the
% index of top 1000 genes is stored in 'feature_with_mRMr_d' vector.
% [1] http://www.stats.uwo.ca/faculty/aim/2015/9850/microarrays/FitMArray/chm/Golub.html
% [2] https://kr.mathworks.com/matlabcentral/fileexchange/14608-mrmr-feature-selection--using-mutual-information-computation-