Wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Introduction to Deep Learning

Total questions: 10

Worksheet time: 10mins

Name
Class
Date
1.

What if we would like to have prediction output (binary classification) represented by probability, which activation function is the best choice?

a)

tanh

b)

ReLu

c)

Sigmoid

d)

Linear

2.

In the context of deep learning, computer determines derivative of a given function using mathematical formula

a)

True

b)

False

3.

Given a deep neural network shown in the figure, what is the dimension of weight at the 3rd layer?

a)

5 x 4

b)

4 x 5

c)

4 x 3

d)

3 x 4

4.

We can directly pass the matrix representation of a color image as an input of the deep neural network

a)

True

b)

False

5.

Given a color image of size 120 x 80 pixels, what is the dimension of its feature vector?

a)

9,600

b)

28,800

c)

8,400

d)

25,200

6.

What is CORRECT about gradient descent?

a)

It returns the optimum parameters that minimize the cost function

b)

It returns the optimum parameters that maximize the cost function

c)

It returns the optimum parameters that minimize the loss function

d)

It returns the optimum parameters that maximize the loss function

7.

The minimum point is the point that slope changes from negative to positive

a)

True

b)

False

8.

What is NOT the property of sigmoid function?

a)

Input is any real number

b)

Output is a real number in range between 0 to 1

c)

Nearly linear when input is close to zero

d)

Slope is close to zero when input is close to zero

9.

What is the limitation of perceptron?

a)

Cannot solve non-linearly separable problem

b)

Cannot handle very large data

c)

Assume normal distribution

d)

Assume independent of features

10.

What if the learning rate is too high?

a)

Model is difficult to converge

b)

Model consumes more computational resources

c)

Model takes longer time to converge

d)

Model is difficult to generalize