30 Questions to test a Data Scientist on Deep Learning (with solutions)

Whether you are a novice at data science or a veteran, Deep learning is hard to ignore. And it deserves the attention, as Deep learning is helping us achieve the AI dream of getting near human performance in every day tasks.

Given the importance to learn Deep learning for a data scientist, we created a skill test to help people assess themselves on Deep Learning. A total of 644 people registered for this skill test.

If you are one of those who missed out on this skill test, here are the questions and solutions. You missed on the real time test, but can read this article to find out how many could have answered correctly.

Here is the leaderboard for the participants who took the test.

Below is the distribution of the scores of the participants:

You can access the scores here. More than 200 people participated in the skill test and the highest score obtained was 26. Interestingly, the distribution of scores ended up being very similar to past 2 tests:

Clearly, a lot of people start the test without understanding Deep Learning, which is not the case with other skill tests. This also means that these solutions would be useful to a lot of people.

Here are some resources to get in depth knowledge in the subject.

If you can draw a line or plane between the data points, it is said to be linearly separable.

2) Which of the following are universal approximators?

A) Kernel SVM B) Neural Networks C) Boosted Decision Trees D) All of the above

All of the above methods can approximate any function.

3) In which of the following applications can we use deep learning to solve the problem?

A) Protein structure prediction B) Prediction of chemical reactions C) Detection of exotic particles D) All of these

We can use neural network to approximate any function so we called it a universal approximator.

4) Which of the following statements is true when you use 1×1 convolutions in a CNN?

A) It can help in dimensionality reduction B) It can be used for feature pooling C) It suffers less overfitting due to small kernel size D) All of the above

Statement 1: It is possible to train a network well by initializing all the weights as 0 Statement 2: It is possible to train a network well by initializing biases as 0

Which of the statements given above is true?

A) Statement 1 is true while Statement 2 is false B) Statement 2 is true while statement 1 is false C) Both statements are true D) Both statements are false

Even if all the biases are zero, there is a chance that neural network may learn. On the other hand, if all the weights are zero; the neural neural network may never learn to perform the task.

6) The number of nodes in the input layer is 10 and the hidden layer is 5. The maximum number of connections from the input layer to the hidden layer are

A) 50 B) Less than 50 C) More than 50 D) It is an arbitrary value

Since MLP is a fully connected directed graph, the number of connections are a multiple of number of nodes in input layer and hidden layer.

7) The input image has been converted into a matrix of size 28 X 28 and a kernel/filter of size 7 X 7 with a stride of 1. What will be the size of the convoluted matrix?

The size of the convoluted matrix is given by C=((I-F+2P)/S)+1, where C is the size of the Convoluted matrix, I is the size of the input matrix, F the size of the filter matrix and P the padding applied to the input matrix. Here P=0, I=28, F=7 and S=1.  There the answer is 22.

8) In a simple MLP model with 8 neurons in the input layer, 5 neurons in the hidden layer and 1 neuron in the output layer. What is the size of the weight matrices between hidden output layer and input hidden layer?

The size of weights between any layer 1 and layer 2 Is given by [nodes in layer 1 X nodes in layer 2]

9) Given below is an input matrix named I, kernel F and Convoluted matrix named C.