FOUNDATIONS OF

ARTIFICIAL INTELLIGENCE
SCO113
Lecturer: Eric Araka
 Introductions
• Instructor

 Eric Araka
 Tutorial Fellow, School of Engineering, CIT Department
 CIT Building, Room 114
 Email: [email protected]
 Tel: +254727815187 I prefer SMS/WhatsApp

 Students?
About the Course
• Foundations of Artificial Intelligence, SCO113>>>>SCO411 later in the Computer Science
program
• Preliquisites
• Conceptual foundations of Computing
• Programming
• Mathematics
• Set theory, logic, probability, calculus
• Data structures
• Lists, trees, graphs
• Basics of Design and Analysis of Algorithms
• Technical writing and presentation
• Course Objectives
• Your Expectations as a student
• Course Assessment: CAT>30%, Exam>70%, What about attendance? First and last class!!
Course Overview
Main Areas of study
Foundations
Intelligent agents
Problem-solving as State Space Search
Knowledge Representation and Reasoning
Planning
Representing and Reasoning under Uncertainty
Decision-Making
Learning
Sample Applications
• Primary Text: S. Russell and P. Norvig, Artificial Intelligence – A Modern
Approach, 4th edition, 2010
 Definition & Motivations
• Artificial Intelligence is the automation of activities we normally
attribute to human thinking and rationality, such as problem-
solving, decision-making, and learning.
 What is AI about
• Study of computational models of intelligence
• Falsifiable hypotheses about intelligent behaviour
• Construction of intelligent artefacts (agents)
• Mechanization of tasks requiring intelligence
• Exploring the design space of intelligent systems
Business Implications
Societal Implications
 Understanding AI
• In their 1995 classic Artificial Intelligence: A Modern Approach,
Berkeley’s Stuart J. Russell and Google’s Peter Norvig broke AI into
five distinct research areas originating from the Total Turing test:
Machine Learning
Expert Systems
Computer Vision
Natural Language Processing
Robotics
 Machine Learning
• Machine learning (ML) is the science of empowering machines to
make decisions without human intervention. This sub-discipline forms
the backbone of AI, enabling computers to learn and interpret
patterns in images, sounds, and structured data using
multidimensional arrays. ML is further subdivided into four types of
learning:
 Expert Systems
• An expert system (ES) is an artificial agent which leverages pre-
programmed knowledge to offer advice or make decisions. In its simplest
form, we can think of an ES as a complicated decision tree or nested if-then
logic: if x, y, and w happen, we instruct the computer to do z. Though
expert systems don’t enjoy the same hype as machine learning, there are
many reasons why we might prefer an ES over ML:
• An expert system can take advantage of human insights discovered through trial and
error
• Expert systems are more predictable and are less likely to make extreme errors when
faced with previously-unseen inputs
• Expert systems have historically been faster and easier to implement, though ML has
become much more accessible in recent years
 Computer Vision
• Computer vision (CV) is the automatic extraction, analysis, and
interpretation of images or videos. CV converts photos and videos
into numerical arrays, enabling ML algorithms to draw inferences,
make predictions, and even generate new images based on user-
defined inputs.
 Computer Vision Cont’d
• These three innovations have opened the floodgates for new CV use cases, including self-driving
cars and automated retailers (e.g., Amazon Go). As cameras, LIDAR, and other spatial sensors
become less expensive, we’ll soon find ways to alleviate many of our most inefficient processes
using CV.
 Natural Language Processing
• Natural language processing (NLP) is the automatic extraction,
analysis, and generation of human language. NLP algorithms parse
sentences in various ways (e.g., splitting by word, splitting by letter,
reading both left-to-right and right-to-left, etc.) to automatically draw
inferences about the writer’s meaning and intent. NLP’s various use
cases include:
Named entity recognition and conference resolution
Part-of-speech tagging
Reading comprehension & question answering
Machine translation
Text summarization & topic modeling
Spellcheck & autocomplete
 Robotics
• Robotics is the science of designing, constructing, operating, and
applying robots to solve human problems. Robots come in thousands
of shapes and sizes, making it difficult to nail down the precise
meaning of the term.
Most robots rely on expert systems to accomplish their objective, but the
robots of tomorrow will become exponentially more useful by
incorporating machine learning, computer vision, and natural language
processing into their operating systems.
 Russell and Norvig’s framework provides a useful structure for thinking
about AI, but these five categories aren’t meant to be mutually exclusive;
the most exciting innovations of the last decade have occurred within their
intersections.

This disciplinary blending will only become more pronounced as time goes
on: delivery drones, self-driving cars, and artificial general intelligence must
tightly integrate all five disciplines if they are to succeed.

Still, every complicated problem has to be broken down into its core
components before it can be solved, and this five-discipline framework
provides a foundational mental model for understanding AI.
 Going Forward
• By the end of this course, the student should be able to:
• Understand artificial intelligence concept
• Understand problem solving techniques using intelligent computer systems
• Apply knowledge presentation techniques and Artificial intelligence tools to
create intelligent computer systems