Question 1
15
10
2
Insufficient information
Question 2
A team has a dataset that contains 100000 samples for training a feed forward neural network. Suppose they decided to use the mini-batch gradient descent algorithm to update the weights. How many times do the weights get updated after training the network for 10 epochs with a mini-batch size of 1000?
100
1000
100000
10
Question 3
The updated weight,after one iteration, moves past the minimum at A if theweight is initialized at point D
The updated weight,after one iteration, moves past the minimum at A if theweight is initialized at point C
The updated weight,after one iteration, moves towards the minimum at A ifthe weight is initialized at point C
The updated weight,after one iteration, moves away from the minimum at B ifthe weight is initialized at point D
2 more questions in this paper
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.
More on the Deep Learning Quiz 1 16 Oct 2022 Set QPG1 paper
The IIT Madras BS Deep Learning (Deep Learning) Quiz 1 paper sat on 16 Oct 2022, in the September 2022 term, set QPG1: 5 questions for 16 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 1 16 Oct 2022 Set QPG1 at a glance |
|---|---|
| Term | September 2022 term |
| Subject | Deep Learning |
| Course code | BSCS3004 |
| Questions | 5 |
| Marks | 16 |
| Duration | 120 min |
| MCQ | 4 |
| MSQ | 1 |
| Official paper | 2022 Oct: IIT M QUIZ 1 DEGREE QPG3 |
| Negative marking | No negative marking. |
| Updated |