Math  /  Word Problems

QuestionChoose the correct reasons for feature scaling in machine learning:
1. Speeds up gradient descent iterations.
2. Accelerates solving for θ\theta using normal equation.
3. Prevents gradient descent from local optima.
4. Ensures matrix XTXX^{T} X is invertible.

Studdy Solution
Let's evaluate the fourth statement "It prevents the matrix XXX^{} X (used in the normal equation) from being non-invertable (singular/degenerate)."
Feature scaling does not prevent the matrix XXX^{} X from being non-invertable. The invertibility of a matrix is not related to the scale of the features, but to the linear independence of the columns of the matrix.
So, the fourth statement is incorrect.
The correct reasons for using feature scaling in machine learning applications are1. It speeds up gradient descent by making it require fewer iterations to get to a good solution.

View Full Solution - Free
Was this helpful?

Studdy solves anything!

banner

Start learning now

Download Studdy AI Tutor now. Learn with ease and get all help you need to be successful at school.

ParentsInfluencer programContactPolicyTerms
TwitterInstagramFacebookTikTokDiscord