PyQdeck LogoPyQdeckSubjectsSyllabusBlog
Back to the 2026 paper

Module 3: Linear Classification and Advanced Methods

20262m

During backpropagation, the main purpose of propagating the error backward is to (i) Generate new training data (ii) Normalize the input (iii) Remove hidden layers (iv) Compute gradients for updating network weights

Search GoogleAsk AI
Worked SolutionAI Assisted

Answer: (iv) Compute gradients for updating network weights

Backpropagation applies the chain rule from the output layer backward to calculate loss gradients with respect to weights and biases. An optimizer uses these gradients to update the parameters.

Similar questions

MACHINE LEARNINGHow does Back Propagation Rule help in learning in Neural Network?20237mMACHINE LEARNINGExplain the backpropagation algorithm. How are weights updated in a neural network using gradient descent?20257mArtificial intelligenceDiscuss how backpropagation helps train a neural network. Use a small example with two layers and a loss function to explain weight adjustment.20247mMACHINE LEARNINGIn neural network. which of the following techniques is used to deal with over fitting? × (i) Dropout (ii) Regularization. (iii) Batch normalization (iv) All of the above20232m
PreviousRidge regression primarily uses which penalty? (i) L0 (ii) L2 (iii) L1 (iv) EntropyNextLDA generally assumes that different classes have (i) Different covariance matrices (ii) No covariance (iii) The same covariance matrix (iv) Identical means
AI LearningWeb Platform

Coursify — Personal AI Course Generator

Struggling with a difficult subject or concept? Turn any engineering topic into a structured course with interactive lessons, quizzes, and research-backed explanations.

Try Coursify Free