Checklist NOAI Singapore 2025 Final · Task 1
Linear Regression Using Gradient Descent
Implement batch gradient descent for linear regression in NumPy.
The task
Question 1 (15 marks) explains the gradient-descent update rule for linear regression and asks for linear_regression_gradient_descent(X, y, alpha, iterations), which returns the coefficient vector rounded to four decimal places, for the fixed example X = [[2, 2], [2, 4], [2, 6]], y = [2, 4, 6], alpha = 0.01, 1,000 iterations.
Abridged by SOTA from the official materials. The official statement has the exact rules, and it wins wherever this summary differs.
At a glance
- You get
- NumPy arrays X (with an intercept column) and y, learning rate and iteration count.
- You submit
- A NumPy array of coefficients rounded to four decimals.
- Rules
- Python 3.9 standard library and NumPy only.
- Format
- NOAI 2025 competition day, 8 March 2025, NTU College of Computing and Data Science; 2.5 hours; Section 1 (MCQs) and Section 2 (three programming questions, 80 marks).