Wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Intro to Neural Networks Review

Total questions: 29

Worksheet time: 16mins

Name
Class
Date
1.

Which of these are reasons for Deep Learning recently taking off? (Check the three options that apply.)

a)

We have access to a lot more computational power.

b)

Neural Networks are a brand new field.

c)

We have access to a lot more data.

d)

Deep learning has resulted in significant improvements in important applications such as online advertising, speech recognition, and image recognition.

2.

2. The job of which of the following layer is to acquire data and feed it to the neural network?

a)

Input

b)

Hidden

c)

Output

d)

Last

3.

Which is the correct structure of a Neural Network?

a)

Output, Hidden Layer, Input

b)

Hidden Layer, Input, Output

c)

Input, Hidden Layer, Output

4.

How many hidden layers have the following Neural network

a)

4

b)

5

c)

6

d)

7

5.

Which of the following statements is true?

a)

The deeper layers of a neural network are typically computing more complex features of the input than the earlier layers.

b)

The earlier layers of a neural network are typically computing more complex features of the input than the deeper layers.

6.

What allows a neural network to learn non-linearly separable problems?

a)

Having more than one neuron

b)

Having more than one layer

c)

Having enough training data

d)

Training for a long time

7.

What does a neuron, the basic unit of a neural network, do?

a)

Performs a multiplication on its inputs

b)

Computes a weighted sum of its inputs, and outputs a nonlinear function of this sum

c)

Computes the maximum of its inputs, and outputs this maximum

d)

Generates a random number between 0 and 1, and outputs this number

8.

If a neural network is overfitting, what strategies would help? Select all that apply.

a)

Introducing dropout

b)

Reducing the number of layers in the model

c)

Increasing the learning rate

d)

Increasing the size of the training data

9.

The most suitable activation function for hidden layer

a)

Sigmoid

b)

ReLu

c)

Softmax

d)

tanh

10.

Which one of these plots represents a ReLU activation function?

a)
b)
c)
d)
11.

Given the neural network inputs and weights and assuming no bias and linear activation, what would the output be?

a)

3

b)

-2

c)

5

d)

-4

12.

Given the neural network inputs and weights and assuming no bias and linear activation, what would the output be?

a)

7

b)

-11

c)

18

d)

5

13.

Backpropagation calculates the ____ and propagates it back to earlier layers.

a)

value

b)

error

c)

data

14.

Control the strength of the connections between the neurons

a)

Artificial Intelligence

b)

Bias

c)

Neuron

d)

Weight

15.

Find the ideal choice of activation function for output layer for predicting multiple classes

a)

Softmax

b)

Relu

c)

Sigmoid

d)

Tanh

16.

Constant which helps the model in a way that it can fit best for the given data

a)

Weight

b)

Neuron

c)

Bias

d)

Layers

17.

Collection of 'neurons' operating together at a specific depth within a neural network

a)

Bias

b)

Weight

c)

Neuron

d)

Layers

18.

When an ENTIRE dataset is passed forward and backward through the neural network only ONCE

a)

One epoch

b)

One batch

c)

One iteration

19.

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

20.

Which is the best output configuration for a model tasked with classifying a person's mood, e.g. angry, happy, sad etc. by the tone of their voice?

a)

One neuron with sigmoid

b)

Multiple neurons with softmax

c)

One neuron with linear output

d)

None of these

21.

Deep learning algorithm for sequential problem

a)

CNN

b)

ANN

c)

DBN

d)

RNN

22.

The number of batches needed to complete one epoch

a)

Iterations

b)

Epochs

c)

Batch

23.

The activation of each neuron in a layer is determined by the __________ of the activations of all the neurons in the previous layer.

a)

weighted sum

b)

sum

c)

level

24.

What is gradient descent?

a)

a way to determine how well the machine learning model has performed given the different values of each parameter

b)

method to increase the speed of Neural Network operation

c)

an optimization algorithm used to find the values of parameters (coefficients) of a function (f) that minimizes a cost function (cost)

d)

different name for activation function

25.

What is activation function?

a)

a way to determine how well the machine learning model has performed given the different values of each parameter

b)

an optimization algorithm used to find the values of parameters (coefficients) of a function (f) that minimizes a cost function (cost)

c)

function describes how computationally expensive is a neural network

d)

function used to enable Neural Network to solve non-linear problems

26.

What activation function is it?

a)

sigmoid

b)

tanh

c)

ReLU

d)

ELU

27.

What activation function is it?

a)

sigmoid

b)

tanh

c)

ReLU

d)

ELU

28.

What activation function is it?

a)

sigmoid

b)

tanh

c)

ReLU

d)

ELU

29.

What did you think of Quizizz?

a)

Eh, not my thing.

b)

It was okay!

c)

Great!