Mbzuai Entry Exam Sample Questions Best May 2026

Question 3 (Bayes for NLP) In a spam detection model, 20% of emails are spam. The word "winner" appears in 60% of spam emails but only 5% of non-spam emails.

Question 4 (Convergence & Distributions) Let ( Z_1, Z_2, ..., Z_n ) be i.i.d. random variables with mean ( \mu ) and variance ( \sigma^2 ). Define the sample mean ( \barZ_n ).

MBZUAI insight: The exam frequently connects pure statistics to optimization. They want you to know that CLT explains why the noisy gradient (from a mini-batch) approximates the true gradient. mbzuai entry exam sample questions best

Best question type: Gradients and convexity.

Sample Q1 (Gradient Descent):

Let ( f(x) = x^4 - 3x^2 ). a) Compute the gradient and Hessian. b) Starting at ( x_0 = 2 ), perform one step of gradient descent with learning rate ( \eta = 0.1 ). c) Is ( f ) convex? Justify.

Sample Q2 (Chain Rule – Backpropagation): Question 3 (Bayes for NLP) In a spam

Given ( z = w_1 \cdot x + b ), ( a = \sigma(z) ) (sigmoid), loss ( L = \frac12(y - a)^2 ). Derive ( \frac\partial L\partial w_1 ).

Search GitHub for "MBZUAI entry exam preparation". Several admitted students have uploaded their practice notebooks. Specifically, look for repositories containing numpy_only/ folders. Question 4 (Convergence & Distributions) Let ( Z_1, Z_2,

Warning: Avoid generic "aptitude test" question banks. They are useless for this exam.