Deep Learning (Data Scientist) Practice Test

Question 1

The human brain is thought to have inspired a neural network model. The neural network is made up of many different components. Each neuron receives an input, processes it, and then outputs.
Which of the following statements represents a genuine neuron correctly?

Accepted Answer

All of the following statements are correct.

Answer

A neuron has several inputs but only one output.

Answer

A neuron has only one input and only one output.

Answer

Multiple inputs and outputs are found in a neuron.

Answer

Although a neuron has only one input, it has several outputs.

Question 2

The most critical stage in constructing a neural network is determining each neuron's weight and bias. You can
 estimate any function if you can figure out how to get the right weight and bias for each neuron. What is the 
best strategy for dealing with this?

Accepted Answer

Iteratively check how far you are from the optimal values after assigning a value, then make little changes to
 the assigned values to improve them.

Answer

Find the best value by combining as many weights and biases as possible.

Answer

Assign random values and pray to God that they are accurate.

Answer

None of the above

Question 3

What are the steps involved in employing a gradient descent algorithm? 1. Reiterate until you find the best weights of network
2. Go to each neurons which contributes to the error and change its respective values to reduce the error
3. Calculate error between the actual value and the predicted value
4.Pass an input through the network and get values from output layer
5. Initialize random weight and bias

Accepted Answer

5, 4, 3, 2, 1

Answer

1, 2, 3, 4, 5

Answer

4, 3, 1, 5, 2

Answer

3, 2, 1, 5, 4

Question 4

"Convolutional Neural Networks can change an input in a variety of ways (rotations or scaling)." True or False:
Is the statement correct?

Accepted Answer

A) False

Answer

B) True

Question 5

Which of the following strategies is similar to dropout in a neural network in terms of operations?

Accepted Answer

Bagging

Answer

Boosting

Answer

Stacking

Answer

None of the above

Question 6

A neural network's non-linearity is caused by which of the following?

Accepted Answer

Rectified Linear Unit

Answer

Convolution function

Answer

Stochastic Gradient Descent

Answer

None of these

Question 7

Which of the following statements concerning model capacity (the ability of a neural network to approximate 
complex functions) is correct?

Accepted Answer

As number of hidden layers increase, model capacity increases

Answer

As learning rate increases, model capacity increases

Answer

As dropout ratio increases, model capacity increases

Answer

None of the above

Question 8

The classification error of test data always lowers as the number of hidden layers in a Multi Layer Perceptron
 increases. Is this statement true or false?

Accepted Answer

A) False

Answer

B) True

Question 9

In a perceptron, what is the sequence of the following tasks?
1. For a sample input, compute an output
2. If the prediction does not match the output, change the weights
3. Initialize weights of perceptron randomly
4.Go to the next batch of dataset

Accepted Answer

3, 1, 2, 4

Answer

1, 2, 3, 4

Answer

1, 4, 3, 2

Answer

4, 3, 2, 1

Question 10

Assume you have to change the settings to minimize the cost function. Which of the following methods could
 be utilized in this situation?

Accepted Answer

Any of these

Answer

Bayesian Optimization

Answer

Exhaustive Search

Answer

Random Search