Logistic Regression
Budget: $250 – $750 CAD
Submit R code where the following procedures are clearly identified:
1. Normalize the feature variable x1
2. Calculate the value of the objective function `(β0, β1).
3. Choose a value of the learning rate η (you should try different values).
4. Initialize the parameter value and calculate the gradient ∇`(β0, β1).
5. Update the parameter value.
6. Check whether gradient ascent has converged. Here, it is much better to look at the convergence of the values of `(β0, β1) than the convergence of the parameters themselves.
7. Complete the implementation of gradient ascent.
8. Predict the labels for a set of test examples.
1. Normalize the feature variable x1
2. Calculate the value of the objective function `(β0, β1).
3. Choose a value of the learning rate η (you should try different values).
4. Initialize the parameter value and calculate the gradient ∇`(β0, β1).
5. Update the parameter value.
6. Check whether gradient ascent has converged. Here, it is much better to look at the convergence of the values of `(β0, β1) than the convergence of the parameters themselves.
7. Complete the implementation of gradient ascent.
8. Predict the labels for a set of test examples.