Module 1: Foundations of AI: Types of AI and Machine Learning

Question 1

What are the 3 broad categories of AI?

Answer 1

1) Artificial Narrow Intelligence
2) Artificial General Intelligence
3) Artificial Super Intelligence

Question 2

What is Artificial Narrow Intelligence? What are the benefits? What are the drawbacks? Provide examples.

Answer 2

AI designed to perform a single or a narrow set of related tasks at a high level of proficiency. (AKA “Weak AI”)

Benefits:
- Boost productivity and efficiency by automating repetitive tasks
- Enabling smarter decision making
- Optimization through trend analysis

Drawbacks:
- Cannot transfer information.

Example: Voice assistants, systems designed to play chess.

Question 3

What is Artificial General Intelligence?

Answer 3

AI designed to closely mimic human intelligence (still has not been achieved). Experts expect AGI systems will do the following things at a level that is similar to or on par with human capabilities:

• Have strong generalization capabilities
• Be able to think, understand, learn and perform complex tasks
• Achieve goals in different contexts and environments

Question 4

What is Artificial Super Intelligence?

Answer 4

A category of AI systems with intellectual powers beyond those of humans across a comprehensive range of categories and fields of endeavor (still has not been achieved). Once developed, the expectation is that it would be:

• Self-aware
• Capable of understanding human emotions and experiences
• Able to experience reality like humans

Question 5

What is Broad Artificial Intelligence?

Answer 5

A category of AI more advanced in scope than artificial narrow intelligence, capable of performing a broader set of tasks, but not sophisticated enough to be considered AGI. Broad artificial intelligence often involves reliance on a group of artificial intelligence systems, capable of working together and combining decision-making capabilities, but still lacking the full human-like capabilities experts expect of AGI.

Question 6

What is Machine Learning?

Answer 6

A branch of AI that leverages the use of data and algorithms to enable systems to learn and make decisions repeatedly. It improves over time without being explicitly instructed or programmed to do so.

Question 7

What are the 3 main types of Machine Learning?

Answer 7

1) Supervised Learning
2) Unsupervised Learning
3) Reinforcement Learning

Question 8

What is the definition of Supervised Learning?

Answer 8

Labeled data grouped or classified into categories via the AI system. (examples: email spam detection, fraudulent transaction data)

Question 9

What is the goal of Supervised Learning?

Answer 9

Accurate predictions of the output of new data.

Question 10

What is needed in order for Supervised Learning to predict accurate results?

Answer 10

High quality labeled data

Question 11

What are some challenges with Supervised Learning?

Answer 11

• It requires a large amount of labeled data, which can be expensive.
• Labeling data can introduce bias.

Question 12

What are the characteristics of a Supervised Learning Model? Provide an example.

Answer 12

A Machine Learning model which learns from a pre-labeled and classified data set. As part of a supervised learning training process, an algorithm analyzes the input data and associated labels to produce an inferred function, which can then become the basis for the system to make predictions based on new, previously unseen inputs. Supervised learning models can also compare their outputs with the correct or intended output, to identify errors and improve their prediction skills.

Example: A model that analyzes images of road signs labeled to define the sign’s meaning or purpose.

Question 13

What are the subcategories of Supervised Learning?

Answer 13

1) Classification Models
The models produce outputs in the form of a specific categorical response; for example, whether an image contains a puppy.

2) Prediction Models predict a continuous value; for example, estimating a stock price.

Question 14

Name the 2 types of Prediction Models

Answer 14

1) Regression Models: a type of prediction model that predict output values by identifying linear relationships between values. For example, a regression model could predict the price of a car based on data such as its year, model, make, features and mileage.

2) Classification Models: a type of prediction model that predict categorical output variables by labeling input data. For example, a classification model could predict whether a future email is spam based on prior emails being labelled “Spam” or “Not spam.”

Question 15

Name a couple of widely used Supervised Learning Models.

Answer 15

1) Support Vector Machine (SVM):
Used for classification and regression tasks but most widely used for classification objectives.

2) Support Vector Regression (SVR):
Most commonly used to produce continuous values.

Question 16

What is the definition of Unsupervised Learning?

Answer 16

Unlabeled data; typically used for pattern detection. (examples: customer segmentation - purchasing preferences; anomaly detection)

Question 17

What is the goal of unsupervised learning?

Answer 17

To find patterns, structures or relationships without predefined targets.

Question 18

What is a challenge with Unsupervised Learning?

Answer 18

Interpretations may be subjective.

Question 19

What are the characteristics of an Unsupervised Learning Model? What are the weaknesses?

Answer 19

Unsupervised learning models do not rely on labeled datasets. Instead, they are designed to identify differences, similarities and other patterns without the aid of human supervision. These models tend to be more cost-efficient and require less effort, but are susceptible to producing less accurate outputs and can display unpredictable behaviors.

Question 20

What are the categories of Unsupervised Learning Models? Name some use cases.

Answer 20

1) Clustering:
Automatically groups data points that share similar or identical attributes; for example, looking for similarities or patterns in DNA samples.

2) Association Rule Learning: Identifies relationships and associations between data points; for example, understanding consumer buying habits.

Use cases:
- Anomaly detection for mechanical faults
- Fraud detection
- Consumer segmentation
- Marketing strategies
- Genetics

Question 21

What is a strength of using Unsupervised Learning?

Answer 21

Discovering hidden patterns and insights in data.

Question 22

Describe two models that are in between Supervised and Unsupervised.

Answer 22

1) Semi-supervised learning models: This approach generally uses a small amount of labeled data and a large amount of unlabeled data. (Examples: Image analysis, speech recognition, and categorization and ranking of web page search results.)

2) Large Language Models (LLMs):
Often rely on semi-supervised learning models. They are a form of AI using deep learning algorithms to create models trained on massive text data sets to analyze and learn patterns and relationships among characters, words and phrases.

Question 23

What is a benefit of using Semi-Supervised Learning?

Answer 23

It reduces the need for expensive manual labeling.

Question 24

What are some challenges with using Semi-Supervised Learning?

Answer 24

• The quality and consistency of the labeled data may be subpar.
• It can be difficult to choose an effective algorithm that can leverage labeled and unlabeled data.

Question 25

What is the definition of Reinforcement Learning?

Answer 25

AI system is rewarded for performing a task well and penalized for not performing it well.

Question 26

What are the characteristics of a Reinforced Learning Model? Provide an example.

Answer 26

Reinforcement learning models use a reward and punishment matrix to determine a correct or optimal outcome. They rely on trial and error to determine what to do or not to do and are rewarded or punished accordingly. These models do not ingest pre-labeled data sets and learn solely through action and repetition, changing or not changing state or by getting feedback from their environment.

(Examples: robotics, gaming, self-driving vehicles)

Question 27

What is a major strength of Reinforcement Learning?

Answer 27

It can learn complex behaviors without explicit supervision.

Question 28

What are some challenges with using Reinforcement Learning?

Answer 28

• It can be difficult to design an appropriate reward mechanism.
• It can be difficult to balance exploration of new actions and exploitation of known good actions.

Question 29

What is Natural Language Processing?

Answer 29

Machine learning technology enabling computers and digital devices to recognize, understand and generate text and speech. It combines computational linguistics and machine learning models to process human language, breaking down human text or speech into smaller parts.

Use cases:
- spam detection
- language translation
- chatbots
- speech to text

Question 30

What is Deep Learning?

Answer 30

A type of machine learning that uses neural networks (mimics the human brain). It can learn and make decisions based on input data.

Use cases:
- Image recognition
- Natural Language Processing
- Speech Recognition

Question 31

What is Generative AI?

Answer 31

AI models that can generate new data based on learning from training data.

Examples:
- OpenAI’s DALL-E
- Stable Diffusion

Question 32

What are Multimodal Models?

Answer 32

AI models that process and integrate information from multiple modalities (text, images, audio, video).

Example:
- Claude (Anthropic’s AI assistant)

Question 33

What are Transformer Models?

Answer 33

Type of neural network architecture that has revolutionized natural language processing. They generate output that is contextually sensitive and allow for continuous conversation.

Examples:
- ChatGPT
- Perplexity AI

Question 34

What is the aim of robotics?

Answer 34

Robotics stems from engineering and computer science and aims to design machines that can perform tasks, usually specific tasks or duties, without human intervention.

Question 35

Explain the Fourth Industrial Revolution (Industry 4.0).

Answer 35

The use of AI in manufacturing and robotics is ushering in the next stage of industry and manufacturing advancements, enabled by increased interconnectivity and smart automation.

Question 36

What is Machine Perception? Provide a use case.

Answer 36

A field in which systems are trained to process sensory information and mimic human senses.

Use case: Improving food production, preparation or storage by creating a system that can touch, smell and taste produce.

Question 37

What is Robotic Process Automation? Provide a use case.

Answer 37

An evolving technology using software robots to automate repetitive and rule-based tasks in business processes.

Use cases: Data entry, form processing

Question 38

What is an Expert System? Name some industries in which Expert Systems are deployed.

Answer 38

A form of AI intended to mimic the decision-making abilities of a human expert in a specific field. These types of systems draw inferences from a knowledge base and rely on AI to replicate the judgment and behavior of a human with specific expertise.

Industries:
- Financial services
- Healthcare
- Agriculture
- Engineering

Question 39

What are the 3 main elements that distinguish an expert system from other AIs?

Answer 39

1) The Knowledge Base:
Typically consists of an organized collection of facts and information from human experts, focused on a specific field or domain. In some cases, the system is also allowed to gather additional information from external sources.

2) The Inference Engine:
Extracts relevant information from the knowledge base and uses it appropriately to solve a problem. Expert systems normally use a rule-based approach that maps data from the knowledge base to a series of rules, which the system uses to make decisions in response to input. Expert systems often include a module that allows users to review its decision-making process.

3) The User Interface:
Allows the end user to interact with the expert system. The user provides an input, like a problem or question, and obtains an output (resolution).

Question 40

What are Linguistic Variables?

Answer 40

They describe concepts in natural language terms, such as “low,” “medium,” or “high” and “warm,” “hot,” or “very hot.”

Question 41

What are Fuzzy Rules?

Answer 41

Fuzzy rules express relationships between variables using if-then statements. For example, a rule might state, “If the temperature is ‘very hot,’ then set the fan speed to ‘high.’”

Question 42

Describe Fuzzy Logic Systems and provide some examples.

Answer 42

Fuzzy logic systems employ fuzzy inference mechanisms to make decisions based on the fuzzy rules and input data. These systems follow a few standard steps:

1) Fuzzification, where input data is converted into fuzzy data sets.

2) Rule evaluation, which determines the degree of matching between the rules and input data.

3) Aggregation, where rule outputs are combined.

4) Defuzzification, the process by which fuzzy outputs are converted back into specific values.

Examples:
- Climate control systems
- Image recognition systems
- Traffic management systems