Optimization Techniques — past-year questions
Deep Learning (CSC701) · Semester 7 · Module 2 · AIML & Data Science
7 past-year questions on Optimization Techniques have appeared in Mumbai University CSC701 papers between 2023–2026, 11 times in total. Every question is shown in full below with its marks and repeat count. Model answers require a free account.
Questions asked on Optimization Techniques
- 1.
What are the different types of Gradient Descent methods, explain any three of them.
10M3× seenlast asked 2025 - 2.
Explain Gradient Descent in Deep Learning.
5M3× seenlast asked 2025 - 3.
Discuss the role of gradient descent in neural network learning.
5M1× seenlast asked 2026 - 4.
Explain the learning process in a neural network. How does a neural network update its weights during training? Describe the role of forward propagation, loss calculation, backpropagation, and optimization in this learning process.
10M1× seenlast asked 2025 - 5.
Explain the gradient descent algorithm used in neural network. Also discuss types of gradient descent in detail.
10M1× seenlast asked 2025 - 6.
Explain Stochastic Gradient Descent and momentum based gradient descent optimization techniques.
10M1× seenlast asked 2023 - 7.
Suppose we have N input-output pairs. Our goal is to find the parameter w that predicts the output y from the input x according to some function y = x^w. Calculate the sum-of-squared error function E between predictions y and inputs x. The parameter w can be determined iteratively using gradient descent. For the calculated error function E, derive the gradient descent update rule w = w - α(dE/dw).
5M1× seenlast asked 2023
Want the answers to these questions?
The questions above are free to read. Create a free account to get AI model answers for Deep Learning, a curated set of the questions that matter most, flashcard revision, and a study plan built around your exam date.