mattnedrich / gradientdescentexample Goto Github PK

Running the file gives this error. I am a beginner can't get around this. Please help !

dear matt:
i am a beginner in machine learning.Thanks for your code,make me learn a lot.
i'm interested in the dynamic graph you made,and try to recurrence it.But when i learn and use "matplotlib.animation",i met some problms.i think,if you can give me your animation code,it will be of great help to me.
thank you very much!:)

Hello,

I am trying to run this python code but I am receiving an error in the following line of code

print "Starting gradient descent at b = {0}, m = {1}, error = {2}".format(initial_b, initial_m, compute_error_for_line_given_points(initial_b, initial_m, points))

I change Learning rate to 0.0005, and i get the following warning message:
gradient_descent_example.py:23: RuntimeWarning: invalid value encountered in double_scalar
new_m = m_current - (learningRate * m_gradient)
.
And this is result:
"After 10000 iterations b = nan, m = nan, error = nan"
How to fix it???

Unable to open gif
https://github.com/mattnedrich/GradientDescentExample/blob/master/gradient_descent_example.gif

Hi matt , thanks for your great example it's really helped me a lot , I was wondering if you have the codes for the visualisation (plots) you have used to demonstrate gradient descent , as that would help me have a deeper understanding of how it works.
many thanks