MauryaHub PYQ Practice

Deep Learning Practice · Quiz 2 · Sep 2024

Deep Learning Practice · Quiz 2 · Sep 2024

← Course papers · Start practice / exam

Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.

0 / 16 published solutions

Question 173 MSQ · 3.0 marks

At training time, consider a training sample, "this is good", where each word is a token. At the last time step (while processing "good"), the word probabilities output by the RNN for these three tokens are:
Source diagram or notation
Which of the following are true?
6406533484216.Source diagram or notation
6406533484217.Source diagram or notation
6406533484218.Source diagram or notation
6406533484219.Source diagram or notation
      **DLP** **Section Id :** 64065374264 **Section Number :** 10 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 16 **Number of Questions to be attempted :** 16 **Section Marks :** 50 **Display Number Panel :** Yes **Section Negative Marks :** 0 **Group All Questions :** No **Enable Mark as Answered Mark for Review and** No **Clear Response :** **Section Maximum Duration :** 0 **Section Minimum Duration :** 0 **Section Time In :** Minutes **Maximum Instruction Time :** 0

A published solution is not available for this question yet.

Report a correction for Q173

Question 175 MCQ · 4.0 marks

Source diagram or notation
6406533484222.Source diagram or notation
6406533484223.Source diagram or notation
6406533484224.Source diagram or notation
6406533484225.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q175

Question 176 MCQ · 4.0 marks

Source diagram or notation
6406533484242.
(2, 3, 4, 1)
6406533484243.
(1, 3, 5, 1)
6406533484244.
(3, 5, 1)
6406533484245.
(3, 1, 1, 5)

A published solution is not available for this question yet.

Report a correction for Q176

Question 177 MCQ · 4.0 marks

Source diagram or notation
6406533484254.
32 × 25
6406533484255.
32 × 26
6406533484256.
16 × 32 × 50
6406533484257.
50 × 3

A published solution is not available for this question yet.

Report a correction for Q177

Question 178 MCQ · 4.0 marks

If an audio is of duration 10 seconds and sample rate is 48KHz, what happens to the length of audio in samples if the audio is downsampled to 16KHz?
6406533484262.Source diagram or notation
6406533484263.Source diagram or notation
6406533484264.Source diagram or notation
6406533484265.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q178

Question 179 MCQ · 4.0 marks

If the current learning rate is 0.002 and the maximum learning rate to be achieved in 1000 steps is 0.004, what should be the step size for a linear learning rate scheduler?
6406533484274.
0.0002
6406533484275.
0.00002
6406533484276.
0.0000002
6406533484277.
0.000002

A published solution is not available for this question yet.

Report a correction for Q179

Question 180 MSQ · 3.0 marks

What is the correct order of training commands?
6406533484246.Source diagram or notation
6406533484247.Source diagram or notation
6406533484248.Source diagram or notation
6406533484249.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q180

Question 181 MCQ · 3.0 marks

To quantize the Whisper model to 8-bit integer during loading in Hugging Face, which of the following arguments should be passed?
6406533484226.Source diagram or notation
6406533484227.Source diagram or notation
6406533484228.Source diagram or notation
6406533484229.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q181

Question 182 MCQ · 3.0 marks

Which of the following models can be used to obtain segments for speaker diarization?
6406533484230.
Whisper
6406533484231.
Wav2Vec
6406533484232.
Speecht5
6406533484233.
GPT-3

A published solution is not available for this question yet.

Report a correction for Q182

Question 183 MCQ · 3.0 marks

Which of the following arguments should be passed during dataset loading to avoid loading the full dataset at once?
6406533484234.Source diagram or notation
6406533484235.Source diagram or notation
6406533484236.Source diagram or notation
6406533484237.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q183

Question 184 MCQ · 3.0 marks

Which of the following loss functions can be used for speaker classification?
6406533484238.Source diagram or notation
6406533484239.Source diagram or notation
6406533484240.Source diagram or notation
6406533484241.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q184

Question 185 MCQ · 3.0 marks

If a dataset has 25600 samples, batch size is 100, each epoch processes the whole dataset only once, and gradient accumulation is set to 32, how many updates does the model make?
6406533484250.
16
6406533484251.
256
6406533484252.
32
6406533484253.
8

A published solution is not available for this question yet.

Report a correction for Q185

Question 186 MCQ · 3.0 marks

Which of the following functions can be used to replace certain values in a PyTorch tensor?
6406533484258.Source diagram or notation
6406533484259.Source diagram or notation
6406533484260.Source diagram or notation
6406533484261.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q186

Question 187 MCQ · 3.0 marks

Which of the following trainers is commonly used for ASR sequence-to-sequence training?
6406533484266.
ASRTrainer
6406533484267.
Seq2SeqTrainer
6406533484268.
LanguageModelTrainer
6406533484269.
ClassificationTrainer

A published solution is not available for this question yet.

Report a correction for Q187

Question 188 MCQ · 3.0 marks

What type of model is HiFi-GAN?
6406533484270.
Text-to-Text model
6406533484271.
Vocoder
6406533484272.
Decoder
6406533484273.
Classifier

A published solution is not available for this question yet.

Report a correction for Q188

Question 189 MCQ · 3.0 marks

Which of the following should be done when a CUDA Out of Memory error is encountered during training?
6406533484278.Source diagram or notation
6406533484279.Source diagram or notation
6406533484280.Source diagram or notation
6406533484281.Source diagram or notation
      **SPG** **Section Id :** 64065374265 **Section Number :** 11 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 10 **Number of Questions to be attempted :** 10 **Section Marks :** 30 **Display Number Panel :** Yes **Section Negative Marks :** 0 **Group All Questions :** No **Enable Mark as Answered Mark for Review and** No **Clear Response :** **Section Maximum Duration :** 0 **Section Minimum Duration :** 0 **Section Time In :** Minutes **Maximum Instruction Time :** 0

A published solution is not available for this question yet.

Report a correction for Q189