When building complex systems like neural networks, checking portions of your work can save hours of headache. Here we'll check our gradient computations.
When building complex systems like neural networks, checking portions of your work can save hours of headache. Here we'll check our gradient computations. Supporting code: http://nbviewer.ipython.org/github/stephencwelch/Neural-Networks-Demysitifed/blob/master/Part%205%20Numerical%20Gradient%20Checking.ipynb Link to excellent Stanford tutorial: http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial In this series, we will build and train a complete Artificial Neural Network in python. New videos every other friday.