wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Machine Learning 101

Total questions: 20

Worksheet time: 14mins

Name
Class
Date
1.

Machine Learning is a subfield of Artificial Neural Networks.

a)

TRUE

b)

FALSE

2.

Which of the following belong to Machine Learning?

a)

Supervised Learning

b)

Unsupervised Learning

c)

Reinforcement Learning

d)

Knowledge Graph

3.

When shall we use machine learning to solve a given real world problem?

a)

When the problem changes over time

b)

When we can't explain human expertise in the form of programming logic

c)

When humans lack of expertise and need to rely on historical data

d)

When Google, Microsoft and Amazon are betting on Machine Learning as the next big thing

4.

Deep Learning is a subfield of Machine Learning.

a)

TRUE

b)

FALSE

5.

Why did deep learning take off only in the most recent decade?

a)

Big data - Having more data due to the digitization of data

b)

The advancement and affordability of digital storage

c)

The rise of computing power (specialized processors such as graphics processing units or GPUs)

d)

Because Geoffrey Hinton, Yoshua Bengio and Yann LeCun only started researching into Deep Learning in recent years

6.

Traditional software in the form of Rule-based system uses handcrafted programming logic as knowledge representation.

a)

TRUE

b)

FALSE

7.

Unsupervised learning looks for previously undetected patterns in a data set with no pre-existing labels and with a minimum of human supervision.

a)

TRUE

b)

FALSE

8.

Which of the following are TRUE about Supervised Learning?

a)

Supervised learning is the machine learning task of learning a function that maps an input to an output based on example input-output pairs.

b)

Supervised learning algorithms are trained using labeled data.

c)

In Supervised Learning, we normally have two sets of problems, Classification and Regression.

d)

Supervised learning requires minimum human annotated data

9.

Reinforcement Learning models learn by a continuous process of receiving rewards and punishments on every action taken.

a)

TRUE

b)

FALSE

10.

As opposed to Supervised Learning, Unsupervised Learning and Reinforcement Learning do not rely on human annotated data (data labeled by human).

a)

TRUE

b)

FALSE

11.

What is missing from the area with "?" mark?

a)

Learn from labeled data

b)

Learn from mistakes

c)

Learn from human experience

d)

Learn nothing

12.

Which statement is WRONG about Deep Learning?

a)

Deep learning enables computers to learn from experience & understand the world in terms of a hierarchy of concepts

b)

Backpropagation helps to calculate the gradient of a loss function with respects to all the weights in the network

c)

Deep Learning is Symbolic AI

d)

Deep Learning involves training neural networks with many layers of units

13.

The term Artificial Intelligence was first coined by John McCarthy in 1956 when he held the first academic conference on the subject at Dartmouth College in Hanover, New Hampshire.

a)

TRUE

b)

FALSE

14.

Symbolic AI which is also known as Classical Artificial Intelligence or Good Old Fashioned AI (FOFAI) displays human like intelligence thanks to the hand-crafted rules and logic programmed by software engineers based on subject matter experts' design.

a)

TRUE

b)

FALSE

15.

The way how Connectionist AI (Neural Net based Deep Learning) works is instead of programming, you show computer lots of examples so that it changes the connection strengths and learns to produce the right answers without you ever programming.

a)

TRUE

b)

FALSE

16.

The most common Unsupervised Learning method is cluster analysis, which is used for exploratory data analysis to find hidden patterns or grouping in data.

a)

TRUE

b)

FALSE

17.

Which are TRUE about Unsupervised Learning?

a)

Clustering and Association are two types of Unsupervised Learning

b)

Four types of clustering methods are 1) Exclusive 2) Agglomerative 3) Overlapping 4) Probabilistic

c)

Unsupervised Learning also known as Self-supervised Learning

d)

Unsupervised Learning normally applies to gaming

18.

Which statement is WRONG about Reinforcement Learning?

a)

Reinforcement Learning is normally applied in gaming and robotics

b)

Self-supervised Learning is Reinforcement Learning

c)

Markov Decision Process and Q-learning are Reinforcement Learning

d)

DeepMind AlphaGo that has defeated human Go world champions was trained by using Reinforcement Learning

19.

Supervised Learning normally is associated with Predictive Analytics that make prediction about the future.

a)

TRUE

b)

FALSE

20.

Unsupervised Learning normally is associated with Descriptive Analytics that aims to gain knowledge from the data.

a)

TRUE

b)

FALSE