Consider a dataset with 150 samples and a batch size of 15. If each minibatch iteration contributes
an average loss of 0.4, what will be the total loss after 15 epochs?
A published solution is not available for this question yet.
If you use hierarchical softmax with a binary tree where each leaf node represents a word in the
vocabulary, and the vocabulary size (V ) is 16000, how many binary classifiers are needed?
A published solution is not available for this question yet.
In a Skip-gram model with a vocabulary size V = 100, an embedding dimension D = 10, and a
window size of 3 (on each side), using negative sampling with 5 negative samples per positive
sample, what is the total number of parameters in the model?
A published solution is not available for this question yet.
In the context of unsupervised pretraining of artificial neural networks, which of the following
statements accurately describes the role and benefits of using unsupervised pretraining
techniques for initializing a neural network?
6406533044537.
Unsupervised pretraining methods help in identifying patterns in unlabeled
data, which can be used to initialize weights and reduce the risk of overfitting in the subsequent
supervised training phase.
6406533044538.
The primary purpose of unsupervised pretraining is to generate synthetic data
that can be used to expand the training dataset for the neural network, leading to more robust
performance.
6406533044539.
Unsupervised pretraining enables the network to learn a hierarchical
representation of data, which can be fine-tuned with supervised learning, enhancing the model’s
generalization capabilities.
6406533044540.
Using unsupervised pretraining techniques ensures that the neural network
can skip the initial training phase, directly achieving high accuracy on test data without further
training.
A published solution is not available for this question yet.
Given a matrix A with dimensions p × q, which of the following statements is NOT true regarding
the rank-k approximation of A obtained through Singular Value Decomposition (SVD)?
Consider an encoder-decoder model trained with a batch size of 64. Each input sequence has a
length of 12 tokens, and each output sequence has a length of 18 tokens. How many
computational steps do the encoder and decoder take per batch respectively during training?
6406533044569.
768, 1152
6406533044570.
1152, 768
6406533044571.
12, 18
6406533044572.
18, 12
6406533044573.
12, 1
6406533044574.
1, 18
A published solution is not available for this question yet.
In the context of the Transformer model’s encoder-decoder architecture, which of the following
statements are correct?
6406533044589.
The encoder processes the entire input sequence at once at a particular time
step, and its output serves as the context for the decoder during generation.
6406533044590.
The multi-head attention mechanism in the decoder allows the model to focus
on different parts of the encoder’s output while generating the sequence.
6406533044591.
The decoder applies self-attention over its entire sequence of inputs without
any restrictions, allowing it to consider all future tokens at once.
6406533044592.
The decoder’s self-attention mechanism includes a masking component to
prevent attending to future positions, ensuring the model generates outputs one step at a time.
A published solution is not available for this question yet.
Based on the above data, answer the given subquestions.
6406533044565.
3 × 2
6406533044566.
3 × 4
6406533044567.
4 × 3
6406533044568.
2 × 4
**Programming in C**
**Section Id :** 64065364134
**Section Number :** 6
**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**
No
**Clear Response :**
**Maximum Instruction Time :** 0
A published solution is not available for this question yet.
