tjaskula / coursera Goto Github PK

I am attempting to submit the gradient descent function in week 2 and when pressing submit it gives me a Type Erro saying "not all arguments converted during string formatting". If it changes anything I am using 2 functions for getting my answer which it originally only used 1 function.

grad = (1 / m) * sum((h - y) .* X) can be instead of X' * (h - y) / m
Maybe the J also can be optimized in this way.

Feature Normalization unit test not pass

I wanted the Coursera ML exercise files but I had to quit since I had to clone the entire repository which is pretty huge considering the amount of free network data available.
Please considering splitting different courses/specializations into different repositories

I think that:

	z2t = [1; Theta1 * a1t];
       d2t = Theta2' * d3t .* sigmoidGradient(z2t);

should be:

    z2t = Theta1 * a1t;
    d2t = Theta2' * d3t .* [1; sigmoidGradient(z2t)];

You do not add 1 to compute z2.

i'm a novice user of matlab. though i'm following this same code and i've even plotted data in the matlab window using the plotdata command still when i try submitting the code it says "correct your code and resubmit" . i cannot figure out where am i making the mistake. if anyone can help i willl be grateful. below i'm attaching the screenshot of my code and error
Thanks