Indian Institute of Technology Madras
BS Degree Programme · Examination & Study Paper
Introduction to Deep Learning and Generative AI
Parameter counts, CNNs & Inception
Examination Instructions & Guidelines
- Solve on notebook/paper first before checking solutions.
- NAT: Numerical response. No negative marking.
- Scientific calculator allowed for all calculations.
- Official answer key is sealed at the end of this sheet.
Useful Reference Data for this Paper
Note: In all the questions, assume necessary imports wherever applicable.
Q1NAT2 Marks·Write the number
Your answer:Read the passage below, then answer Q2–Q5

Based on the above data, answer the given subquestions.
Q2NAT3 Marks·Write the numberHow many trainable parameters are there in the first convolutional layer including bias (conv1)?
Your answer:- Q3NAT1 Mark·Write the number
What is the total number of trainable parameters in the pooling layers(pool1 and pool2)?
Your answer: - Q4NAT1 Mark·Write the number
How many parameters (weights and biases) does the first fully connected layer (fc1) have?
Your answer: - Q5NAT1 Mark·Write the number
What is the total number of convolution filters used in this CNN?
Your answer: Read the passage below, then answer Q6–Q8

Based on the above data, answer the given subquestions.
Q6NAT3 Marks·Write the number
Your answer:- Q7NAT3 Marks·Write the number
Your answer: - Q8NAT3 Marks·Write the number
Your answer: