Question 271 MCQ · 4.0 marks
What is the annualized rate of return of an investment of 100 units that promises to return 200
units in 10 years?
10%
7.18%
5.97%
3.76%
A published solution is not available for this question yet.
Large Language Models · Quiz 1 · Sep 2024
Large Language Models · Quiz 1 · 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 / 22 published solutions
Question 272 MCQ · 4.0 marks
A financial advisor tells you that you can become a millionaire if you start investing early. You start
to deposit 25,000 units every year in a savings account which earns 8% annual interest. What is the
earliest year at which your account balance reaches a million units? (Assume you don’t make any
withdrawals in between)
40
25
19
15
**LLM**
**Section Id :** 64065369323
**Section Number :** 14
**Section type :** Online
**Mandatory or Optional :** Mandatory
**Number of Questions :** 10
**Number of Questions to be attempted :** 10
**Section Marks :** 40
**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.
Question 274 MCQ · 0.0 marks
General Note:
• If you find the given information is insufficient in any of the Numerical Answer Type (NAT)
questions, enter -1 as the answer.
• In all your calculations, take at least two digits. For example, if the intermediate result is
1.860875, then take it as 1.86 to the next step.
Instructions has been mentioned above.
This Instructions is just for a reference & not for an evaluation
A published solution is not available for this question yet.
Question 275 MCQ · 2.0 marks
Teacher forcing for training an transformer model is:
mandatory.
optional.
A published solution is not available for this question yet.
Question 276 MCQ · 2.0 marks
Choose the correct statements regarding transformer architecture:
Residual connections are practically optional in a transformer model with 10
encoder layers and 10 decoder layers.
Having multiple heads helps in capturing different relationships between
input tokens.
One hot encoding is a good choice for position encoding.
Batch normalization can be used instead of layer normalization.
None of these.
A published solution is not available for this question yet.
Question 277 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
Assume the model has two layers (N = 2). Calculate the total number of parameters in the model
(excluding the embedding layer and output layer). Moreover, no bias was added to the neuron in
the FFNN layers.
A published solution is not available for this question yet.
Question 278 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
How many parameters does the output layer have?
A published solution is not available for this question yet.
Question 279 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
How many parameters does the embedding layer have?
A published solution is not available for this question yet.
Question 280 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
At time step t = 1, the prediction probability for the words “Naan”, “transformer” and “padaththai”
are 0.55,0.15 and 0.2, respectively. What is the probability for the word “rasithen”? If you think, the
given information is insufficient enter -1
A published solution is not available for this question yet.
Question 281 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
Say matrix F is computed by applying batch normalization on X, what will be sum of every element
in first/topmost row of F?
A published solution is not available for this question yet.
Question 282 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
Say matrix F is computed by applying layer normalization on X, what will be sum of every element
in first/leftmost column of F?
A published solution is not available for this question yet.
Question 283 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 284 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 285 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 286 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 287 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 288 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 289 MCQ · 2.0 marks
Based on the above data, answer the given subquestions.
What will be the shape of positional embedding?
64 × 128
64 × 4
12 × 128
512 × 768
None of these.
A published solution is not available for this question yet.
Question 290 MCQ · 2.0 marks
Based on the above data, answer the given subquestions.
32 × 32
64 × 32
128 × 16
128 × 32
8 × 32
None of these.
A published solution is not available for this question yet.
Question 291 MCQ · 2.0 marks
Based on the above data, answer the given subquestions.
16 × 16
32 × 32
64 × 64
128 × 128
None of these.
A published solution is not available for this question yet.
Question 292 NAT · 4.0 marks
A published solution is not available for this question yet.
Question 293 NAT · 3.0 marks
A published solution is not available for this question yet.