training of sparse neural network

Description: in these codes we lustrate in details how we can train a single hidden layer feedforward net for both classification and regression by solving a linear problem with L1 norm optimization.
In these references you will find the most important math that you need to develop the code.

[1] R. G. Baraniuk, “<Compressive Sensing(lecture notes).pdf>,” no. July, pp. 118–121, 2007.
[2] M. W. Fakhr, E. N. S. Youssef, and M. S. El-Mahallawy, “L1-regularized least squares sparse extreme learning machine for classification,” 2015 Int. Conf. Inf. Commun. Technol. Res. ICTRC 2015, no. April, pp. 222–225, 2015.
[3] G. Huang, S. Member, H. Zhou, X. Ding, and R. Zhang, “Extreme Learning Machine for Regression and Multiclass Classification,” vol. 42, no. 2, pp. 513–529, 2012.
[4] C. justin Romberg and Jrom@acm.caltech.edu, “L1 magic toolbox.”