In the context of mini-batch gradient descent, if reducing the size of the minibatch to half makes
your model take thrice as many epochs to reach convergence, how does this affect the total
number of parameter updates compared to using the original mini-batch size? Assume everything
else remains constant.
6406532756993.
The number of updates required increases by 2/3 times.
6406532756994.
The number of updates required increases by six times.
6406532756995.
The number of updates required increases by 3/2 times.
6406532756996.
The number of updates required decreases by 2/3 times.
6406532756997.
The number of updates required decreases by six times.
6406532756998.
The number of updates required decreases by 3/2 times.
A published solution is not available for this question yet.
Consider an ensemble consisting of 5 models, where each model has an individual error rate of
50% on the test set. Assuming a simple majority voting scheme, what is the probability that a
given instance is misclassified by the ensemble?
Assume that the models are independent and their errors are uncorrelated.
A published solution is not available for this question yet.
Given the true outputs for a dataset, y = [1,2,3,4], and the predictions from three different models
(A, B, and C) trained on different subsets of the training data, as follows:
Model A predictions: A = [1.1,1.9,3.1,3.9]
Model B predictions: B = [0.9,2.1,2.9,4.1]
Model C predictions: C = [2,2,3,4]
Calculate the average variance for these models evaluated in a regression task. Assume that each
model uses the same parameters but is trained on different subsets of the training data. (Enter
your answer up to 3 decimal places.)
A published solution is not available for this question yet.
Consider a Convolutional Neural Network (CNN) architecture for image classification with the
following layers:
1. Convolutional layer with 24 filters of size 3 × 3, with a stride of 1 and no padding.
2. Max pooling layer with a pool size of 2 × 2 and a stride of 2.
3. Convolutional layer with 56 filters of size 4 × 4, with a stride of 1 and no padding.
4. Max pooling layer with a pool size of 2 × 2 and a stride of 2.
5. Fully connected layer with 108 neurons.
6. Output layer with 10 neurons (for 10 classes) using softmax activation.
If the input image size is 84 × 84 × 3, and the network has no bias term, how many parameters are
there in the CNN?
A published solution is not available for this question yet.
Suppose you have a vocabulary of 5,000 unique words and you want to train a CBOW model with a
window size of 3 (on each side) and with an embedding dimension of 500. How many parameters
(weights) will the embedding layer have?
A published solution is not available for this question yet.
Assume that your CBOW model outputs a probability distribution over a vocabulary of 10,000
words for a given context. If the correct target word is word number 200, and the model’s
predicted probability for this word is 0.3, calculate the cross-entropy loss for this prediction.
A published solution is not available for this question yet.
In a Skip-gram model with a window size of 2 (on each side), how many **unique** pairs of target and
context words will be generated for the following sentence:
**‘Finish easy questions as early as possible’**
A published solution is not available for this question yet.
In a Skip-gram model with a vocabulary of 20000 words, if you choose a negative sampling rate of
5 negative samples for each positive sample, how many **total** samples will be generated for a
sentence with 10 words and a window size of 2 (on each side)?
A published solution is not available for this question yet.
Based on the above data, answer the given subquestions.
With a total of 20 time steps (T = 20, implying prediction for a word of length 19), what is the total
count of parameters (including bias) within the network?
A published solution is not available for this question yet.
Based on the above data, answer the given subquestions.
If all the parameters (including bias) in the network are initialized to zero, what will be the total
loss after 20 time steps (assume that indices start with 1) for the input [0, 0, 0, 1, 0, 0, 0, 0]\(^{T}\) ?
assume the loss to be cross-entropy at each time step. Write your answer correct to two decimal
places.
A published solution is not available for this question yet.
Consider training a Recurrent Neural Network (RNN) for a sequence prediction task. Which of the
following statements accurately describe challenges in training RNNs?
6406532757020.
RNNs suffer from the problem of ”short-term memory,” where they struggle to
retain information from earlier time steps when processing long sequences, leading to limitations
in capturing long-term dependencies.
6406532757021.
RNNs do not suffer from the problem of ’short-term memory’ and can
effectively retain information from earlier time steps even when processing long sequences.
6406532757022.
Training RNNs requires careful initialization of weights and biases to ensure
stable convergence during training, as poorly initialized weights can lead to gradient saturation
and slow learning.
6406532757023.
Architectural modifications such as Long Short-Term Memory (LSTM) and
Gated Recurrent Unit (GRU) have been introduced to address the problem of ”short-term memory”
in RNNs and improve their ability to capture long-term dependencies.
A published solution is not available for this question yet.
State True or False. GRUs are popular variant of LSTMs in which output and forget gates are
combined.
6406532757024.
TRUE
6406532757025.
FALSE
**Programming in C**
**Section Id :** 64065357855
**Section Number :** 4
**Section type :** Online
**Mandatory or Optional :** Mandatory
**Number of Questions :** 26
**Number of Questions to be attempted :** 26
**Section Marks :** 100
**Display Number Panel :** Yes
**Section Negative Marks :** 0
**Group All Questions :** No
**Enable Mark as Answered Mark for Review and**
Yes
**Clear Response :**
**Maximum Instruction Time :** 0
A published solution is not available for this question yet.
