Training Feedforward DNN — past-year questions
Deep Learning (CSC701) · Semester 7 · Module 2 · AIML & Data Science
6 past-year questions on Training Feedforward DNN have appeared in Mumbai University CSC701 papers between 2023–2026, 10 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 Training Feedforward DNN
- 1.
What is the significance of Activation Functions in Neural Networks, explain different types Activation functions used in NN.
10M4× seenlast asked 2025 - 2.
Comment on the significance of Loss functions and explain different types of Loss functions while training a network.
10M2× seenlast asked 2025 - 3.
Explain the major factors influencing the learning efficiency of a deep neural network.
5M1× seenlast asked 2026 - 4.
Explain how MSE measures prediction error in regression models.
5M1× seenlast asked 2026 - 5.
Discuss the role of a loss function in training a neural network. Compare Mean Squared Error (MSE) and Cross-Entropy Loss in terms of their usage, characteristics, and impact on model performance. In which scenarios would using Cross-Entropy Loss be more appropriate than MSE? Justify your answer with a suitable example.
10M1× seenlast asked 2025 - 6.
What is an activation function? Describe any four activation functions.
10M1× 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.