Quiz Space

Deep Learning · End Term · 30 Apr 2023 · January 2023 term

Question 11: Suppose we divide the available training samples into mi…

Question 11

+3 marksOne or more correct options

Suppose we divide the available training samples into mini batches of size 32 to train a model with mini-batch gradient descent. Assume that we have 33 different machines to train the model. One out of 33 machines acts as a master machine. The actual weight update happens in the master machine. The master machine can send one sample for the rest of the machines along with a copy of the model in its current state to compute the gradients. We call this entire set-up parallelization. Which of the following deep learning architectures can be trained in parallel then?

Select all that apply.

  1. A

    Fully connected Feed forword neural network

  2. B

    Convolutional Neural network

  3. C

    Reccurent Neural Network

  4. D

    Transformers

Show answer

Correct answers

  • A

    Fully connected Feed forword neural network

  • B

    Convolutional Neural network

  • C

    Reccurent Neural Network

  • D

    Transformers

See the whole paperTake it as a mock test

Question 11 of 16 in the IIT Madras BS Deep Learning (Deep Learning) End Term paper sat on 30 Apr 2023, in the January 2023 term (IIT M DEGREE ET1 EXAM QPE2 S1 30 Apr 2023). It carries 3 marks.

This question was also asked in

More questions from this paper

  1. Q1Suppose that we implement a three input Boolean function using the Mc-Culloch Pitts (MP) neuron. The graph below shows …
  2. Q2Consider the following two sentences\ A man was sitting at the bank of the river and gazing at stars in the sky • A man…
  3. Q3Figure question
  4. Q4Figure question
  5. Q5Consider a skip-gram model shown below. Each word in the vocabulary is represented as one-hot vector of size 100×1. The…
  6. Q6Based on the above data, answer the given subquestions.
  7. Q7Suppose that all the elements in the input vector are zero and the corresponding true label is also 0. Further, suppose…
  8. Q8Assume that we use backpropagation to compute the gradient of the loss w.r.t. all the parameters. Then the statement th…
  9. Q9The plot below shows contours of a function f(w, b). Choose the correct statements The plot below shows contours of a f…
  10. Q10Suppose that a model produces zero training error without using any regularization technique. What happens if we use L2…
  11. Q12A text corpus contained the following two sentences.\ In science if you know what you are doing you should not be doing…
  12. Q13Suppose we build a co-occurrence matrix of size m × n, where each row corresponds to a word in the vocabulary and the c…
  13. Q14Consider a simple RNN for a binary sequence classification problem. Consider a simple RNN for a binary sequence classif…
  14. Q15Consider a simple RNN for a binary sequence classification problem. Consider a simple RNN for a binary sequence classif…
  15. Q16Consider the statement “the attention coefficients in RNN based Encoder- Decoder architecture are computed for each tim…