Scribd
Upload
278 views

Artificial Intelligence (AI2002) Course Outline Spring 2023

The document provides information about an Artificial Intelligence course including the instructor details, course objectives, textbook, grading criteria, policies, and tentative weekly schedule. The course aims to help students understand AI principles and techniques, identify and solve problems with intelligent solutions, and examine latest trends in AI and applications.

Uploaded by

Moosa Adnan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
278 views

Artificial Intelligence (AI2002) Course Outline Spring 2023

The document provides information about an Artificial Intelligence course including the instructor details, course objectives, textbook, grading criteria, policies, and tentative weekly schedule. The course aims to help students understand AI principles and techniques, identify and solve problems with intelligent solutions, and examine latest trends in AI and applications.

Uploaded by

Moosa Adnan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

NATIONAL UNIVERSITY

of Computer & Emerging Sciences, Lahore

F A S T S c h o o l o f C o m p u t i n g
AI2002 – Artificial Intelligence
Spring 2023
Instructor Name: Abeeda Akram TA Name: Ali Haider
Email: [email protected] TA Email: [email protected]
[email protected]
Office Location: Old-Admin Block Exam Hall
Office Hours: Wednesday 11:30 to 1:00 PM, Friday 1:00 PM to 3:00 PM

Course Information
Program: BS(CS) Credit Hours: 3 and (1 for Lab) Type: Core Pre-requisites: Data Structures
Class Venue: E&M-16
Class Time: BCS-6E Wed-Fri 10:00 – 11:30
BCS-6F Wed 1:00 - 2:30 PM, Fri 11:30 - 1:00 PM

Course Learning Outcomes (CLOs):


The course learning outcomes of this course are:
1. Understand principles and techniques of artificial intelligence
2. Identify the problems and their solutions with respect to intelligent solutions
3. Model a solution for a given problem using artificial intelligence tools and techniques
4. Examine latest trends in AI and its applications
5. Able to propose and implement AI based state of the art solutions

Course Textbooks:
1. Stuart Russell, Peter Norvig - Artificial Intelligence a Modern Approach - (3rd Edition)
Additional references and books related to the course:
2. George F. Luger - Artificial Intelligence
3. Tom Mitchell Machine Learning

(Tentative) Grading Criteria:


Assignments (10%) Quizzes (10%) Project (10%) Midterms (25%) Final Exam (45%)
• Grading scheme for this course is Absolute under application of CS department's grading policies.
• Minimum requirement to pass this course is to obtain at least 50% absolute marks.

Course Policies:
• Quizzes may be announced or surprised. No Late Submissions or Makeup Quizzes.
• Students bear all the responsibility for protecting their assignments. In case of cheating, both parties
will be considered equally responsible.
• Plagiarism in any work (Labs, Quiz, Assignment, Midterms, and Final Exam) from any source,
Internet or a Student will result in F grade or deduction of absolute marks.
• 80% attendance is required for appearing in the Final exams.
Tentative Weekly Schedule
Topic Details Weak
− Introduction and Applications 1
− Knowledge and Reasoning
Introduction − Blocks world and Predicate Calculus
− Introduction to Agent and Agent Architectures
− PEAS
Blind/Uninformed/Brute-force Search 2
− Depth First Search (DFS)
− Breadth First Search (BFS)
− Iterative Deepening Search (IDS)
− Uniform Cost Search (UCS)
Direction of Search, Branching Factor
Heuristic/Informed Search 3
− Hill Climbing Search
− Best First Search
Strategies for − Algorithm A
State Space − A* Search
Search Informedness, Monotonicity, Admissibility, Optimality, Completeness,
Adversarial Search Algorithms (Game Playing) 4
− Minimax Search
− Alpha-Beta Pruning
− Evaluation Functions
− Move generators and evaluators
Problem Solving by Searching
Evolutionary Search: 5
− Genetic Algorithm
− Genetic Programming
− Automatic/Evolutionary Programming
Classification (ANN) 6-7
− Architecture: Feed-Forward Neural Network and Recurrent Network
− Activation Functions
− Types of Problems for Neural Networks
− Training Algorithms
Introduction − Perceptron Learning Rule
to Machine − Hebb Learning Rule
Learning, − Back Propagation Algorithm (Gradient Descent Learning)
Data Mining, − Issues of ANN
& Data − Recurrent Networks (Elman and Jordon)
Science Clustering 8-9
− k-means and k-medoids algorithm
− Cobweb
Regression 10-11
− Simple and Multiple Linear Regression
− Attribute/Feature Selection
− WEKA - Assignment

You might also like