Deep Learning · End Term · Jan 2023 · AN

For the 2D line drawing, assign consistent labels to all edges and junctions. Enter the labels of the junctions 1, 2, 3 in the text box, in that order. Or enter NIL if the drawing has no consistent label assignment.

Enter a comma separated list of junction labels, or enter NIL. NO SPACES, TABS, DOTS, BRACKETS OR EXTRANEOUS CHARACTERS. **Answer format: X9,Y9,Z9**

Based on the above data, answer the given subquestions.

Based on the above data, answer the given subquestions.

Suppose that all elements in the input vector are zero and the corresponding true label is also 0. Further, suppose that all the parameters are initialized to zero. What is the loss value if cross entropy loss is used? Use natural logarithm ln.

Based on the above data, answer the given subquestions.

Assume that we use backpropagation to compute the gradient of the loss w.r.t. all the parameters. Then the statement that the gradients w.r.t. all the parameters are zero and hence none of the parameters get updated is

Consider a simple RNN for a binary sequence classification problem.

Based on the above data, answer the given subquestions.

What is the loss value? Use cross entropy loss with natural logarithm.

Consider a simple RNN for a binary sequence classification problem.

Based on the above data, answer the given subquestions.

Consider the following two sentences • A man was sitting at the bank of the river and gazing at stars in the sky • A man went to the bank to check his current balance Suppose we get the word representation for the word **bank** in both sentences using CBOW and Skip-Gram model. Choose which of the following are correct statements. The models were trained by building a vocabulary with unique words from the sentences.

Suppose we divide the available training samples into mini batches of size 32 to train a model with 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?

A CNN model takes an input image of size 30×30. The first convolution layer uses 100 kernels(filters) each of size 3 × 3, the output from the first convolution layer is passed as an input to the second convolution layer. The second convolution layer uses 10 kernels each of size 5 × 5. How many parameters are there in the network? Assume stride=1,padding=0 if required.

Consider a skip-gram model shown below. Each word in the vocabulary is represented as one-hot vector of size 100×1. The embedding dimension h is 5×1. Enter the number of parameters (exclude bias) in the entire network

A team has 25600 samples in a dataset for a classification problem. They decided to train the neural network model for 10 epochs with Nesterov Accelerated Gradient descent optimization algorithm with Cross entropy loss. Suppose they use a mini-batch with 32 samples per batch. How many times do the parameter in the network get updated?

Consider the statement “the attention mechanism in RNN based Encoder- Decoder architecture helps the encoder to understand the context of words in a given sentence”. The statement is

A text corpus contained the following two sentences. • In science if you know what you are doing you should not be doing it • In engineering if you do not know what you are doing you should not be doing it Based on the above data, answer the given subquestions.

A text corpus contained the following two sentences. • In science if you know what you are doing you should not be doing it • In engineering if you do not know what you are doing you should not be doing it Based on the above data, answer the given subquestions.

Suppose we build a co-occurrence matrix of size m × n, where each row corresponds to a word in the vocabulary and the columns corresponds to the context of the word. Which of the following could be a valid size of the co-occurrence matrix (select all correct answers)?