What is the impact of using a sigmoid activation function on the gradients when the input to the neuron is a very large negative number?
The output approaches 0 and the gradient approaches 0.
The output approaches 0.5 and the gradient approaches 0.25.
The output approaches 1 and the gradient approaches 0.
The output approaches 0 and the gradient approaches 1.
Why is bias correction needed in the Adam optimizer?
To prevent the learning rate from becoming too large in the early iterations.
To correct the underestimated moving averages of the first and second moments at the beginning of training.
To increase the momentum effect for faster convergence.
To ensure the learning rate remains constant throughout training.
How do skip connections in ResNet work?
By incorporating element-wise addition of the input of a layer to its output
By concatenating the input and output of a layer
By multiplying the input and output of a layer
By removing the input from the output
Sign in with Google — it is free — to see every question with its answer and explanation, practise it in learning mode, or take it as a timed mock test.
The IIT Madras BS Deep Learning (Deep Learning) Quiz 2 paper sat on 16 Mar 2025, in the January 2025 term: 23 questions for 40 marks in 120 minutes. The first 3 questions are below. Sign in with Google — it is free — to see the whole paper with its answers and explanations, in learning mode or as a timed mock test.
| Feature | Deep Learning Quiz 2 16 Mar 2025 at a glance |
|---|---|
| Term | January 2025 term |
| Subject | Deep Learning |
| Course code | BSCS3004 |
| Questions | 23 |
| Marks | 40 |
| Duration | 120 min |
| MCQ | 10 |
| Numerical | 13 |
| Official paper | IIT M DEGREE AN EXAM QDB2 16 Mar 2025 |
| Negative marking | No negative marking. |
| Updated |
