DL- Gradient Descend for Neural network (logistic regression).ipnb : Gradient Descent in Neural Network.(Deeplearning-(Insurance-Data))
Gradient Descent is a term that you will often hear in Neural Network. Indeed, the optimization/learning phase of Neural Network (backpropagation) use gradient descent as a method to update the various weight. The insurance_data.csv is attached here.By using this data here I am predicting the chance of taking insurance by age and affordability..In this data age and afffordability are the features.Scaling is also using on age for improving accuracy. For reducing loss here i am using log loss function and To get range (0,1) by sigmoid function..
In the end we are able to come up with same value of w1,w2 and bias using plain python implimentation of gradient descent function.