Udacity: Intro to Deep Learning with PyTorch:

 

– Logistic Regression:

• Take your data
• Pick a random model
• Calculate the error
• Minimize the error, and obtain a better model

– Calculating the Error Function

– Minimizing the error function

Day 25 of #60daysofudacity

– Gradient Calculation

In order to minimize the error function, we need to take some derivatives. So let’s compute the derivative of the error function. 

sigmoid function :

the error formula is:

E=−m1​∑i=1m​(yi​ln(yi​^​)+(1−yi​)ln(1−yi​^​))