GATE Data Science and Artificial Intelligence Practice Quiz

Question 1

In standard backpropagation for a feedforward neural network, what quantity is propagated backward from the output layer to hidden layers?

Accepted Answer

The gradient of the loss with respect to each layer's pre-activation

Question 2

For a neuron with pre-activation z = w^T x + b and activation a = sigma(z), which expression gives the gradient of the loss L with respect to weight w_i during backpropagation?

Accepted Answer

dL/dw_i = (dL/dz) x_i

Question 3

A network has one hidden layer with tanh activation and a linear output. The loss is mean squared error L = (1/2)(y_hat - y)^2 for one example. If the output neuron computes y_hat = v^T h + c, what is dL/dv?

Accepted Answer

(y_hat - y) h

Question 4

In gradient checking for backpropagation, a parameter theta_i is perturbed by a small epsilon. Which finite-difference approximation is generally preferred for numerically estimating dL/dtheta_i?

Accepted Answer

[L(theta_i + epsilon) - L(theta_i - epsilon)] / (2 epsilon)

Question 5

Consider a hidden layer l with pre-activation z^(l), activation a^(l), and next-layer weights W^(l+1). If delta^(l+1) = dL/dz^(l+1), which expression correctly gives delta^(l)?

Accepted Answer

delta^(l) = ((W^(l+1))^T delta^(l+1)) ⊙ g'(z^(l))

⚠️ Hidden Problematic Habits & Patterns in Exams	✅ How ProSyllabus Analytics Identifies Issues and Provides Tailored Solutions
Focusing too much on hard questions while missing easy, high-scoring ones.	Allows you to see missed easy questions with time spent and revisit frequency details.
Missed correct answers indicate potential oversight or skipped review.	Highlights unmarked correct answers to support a thorough review.
Excessive time spent on specific questions suggests poor time management.	Provides insights on optimal time distribution for improved focus.

GATE Data Science and Artificial Intelligence

AI-Powered Mock Test Analytics

Mock tests aren’t just about scores—they help uncover bad habits. Many students waste time on hard questions with the same marks as easier ones. Fix this with our platform: identify inefficiencies, optimize your strategy, and elevate your performance.