Scribd
Upload
19 views16 pages

AI Lesson 3

The document provides an overview of Artificial Intelligence (AI) systems, focusing on expert systems and machine learning. It defines AI systems as machines that simulate human intelligence and outlines the components and advantages of expert systems, such as high accuracy and fast response times, as well as their disadvantages, including high costs and the need for user training. Additionally, it explains machine learning as a subset of AI that enables machines to learn from data and make decisions, detailing its components and types.

Uploaded by

Beast NKb
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
19 views16 pages

AI Lesson 3

The document provides an overview of Artificial Intelligence (AI) systems, focusing on expert systems and machine learning. It defines AI systems as machines that simulate human intelligence and outlines the components and advantages of expert systems, such as high accuracy and fast response times, as well as their disadvantages, including high costs and the need for user training. Additionally, it explains machine learning as a subset of AI that enables machines to learn from data and make decisions, detailing its components and types.

Uploaded by

Beast NKb
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Artificial

Intelligence
Lesson 3
Understanding AI
Systems: Expert Systems
and Machine Learning
AI
Systems
Exploring the Foundations of
Artificial Intelligence
Definition: AI systems
simulate human intelligence
processes by machines
What is
Artificial Purpose: Enable machines
Intelligen to perform tasks requiring
human-like intelligence
ce
Systems? Components: Data
collection, reasoning,
learning, adaptation
Definition: Expert Systems
mimic human expertise in
specific domains

Understandi Components: Knowledge


ng Expert base, inference engine, user
interface
Systems
Operation: Utilizes rules
and knowledge to provide
advice or solve problems
Knowledge Base:
Repository of domain-specific
knowledge and rules

Componen
Inference Engine:
ts of Reasoning mechanism that

Expert applies rules to data or


queries
Systems
User Interface: Interface
for users to interact with the
expert system
Components of Expert Systems
Medical Diagnosis
System: Utilizes medical

Example knowledge to diagnose


illnesses
of Expert
Legal Advice System:
Systems Provides legal guidance
based on established laws
and cases
They offer high accuracy.

Advanta The results are consistent.

ges of They have very fast response time.


Expert
Systems It is possible for an expert system to have
multiple expertise.

They can indicate the probability of any


suggested solution being correct.
The set up and maintenance costs are
very high.

Disadvanta Users of expert systems require


training to use it correctly.
ges of
Expert They tend to give very cold
responses that may not be appropriate
Systems for some medical situations

They are only as good as


information/facts entered to the
system.
Understanding Machine Learning
Systems
How Machine Learning Different from AI

AI Machine Learning
Represents stimulate This is the practice of
intelligence in machines. making machines to
make decisions without
being programmed to do so.
The aim is to build machines The aim is to make
that are capable to thinking machines that learn through
like humans. data acquisition, so that
they can solve new
problems.
Understanding
Machine Learning
•Systems
Definition: Machine
Learning systems learn from
data to make predictions or
decisions
• Types: Supervised learning,
unsupervised learning,
reinforcement learning
• Components: Data, model,
algorithm, evaluation
Data: Input information used to train
the machine learning model

Compone
Model: Mathematical representation
nts of of patterns in the data

Machine
Learning Algorithm: Mathematical procedure
for training and making predictions

Systems
Evaluation Metrics: Criteria for
assessing the performance of the
model
Image Recognition
Example System: Learns to classify

of images into predefined


categories
Machine
Learning Spam Email Filter:
Identifies spam emails
Systems based on learned patterns
Data Collection: Gather diverse
data sources relevant to the task

Basic Processing: Analyze and preprocess


data to extract meaningful features
Operatio
n of AI Reasoning: Apply rules or
algorithms to make decisions or
Systems predictions

Learning and Adaptation:


Continuously improve performance
based on feedback
Question
s and Any Question?
Discussi
on

You might also like