CS - AI - 16 Weeks Plan

Sixteen Week Plan
Department of Computer Science

Faculty of Computing & Information Technology
GT Road/Hafiz Hayat Campus, University of Gujrat
Title Artificial Intelligence

Code CS-331
Credit hours 3.0
CS courses that include topics of general computing, data structures and algorithms. Familiarity with at least one
Prerequisite
programming language and environment.
Category Core
This course will introduce the basics of artificial intelligence (AI), its scope and application domain. The course will
Course cover topics such as knowledge representation and reasoning formalisms, propositional logic, search methods,
Description learning paradigms, automated reasoning, knowledge based systems, knowledge application and machine learning
techniques and some of deep learning techniques etc.
 To introduce the principles of AI methods.
 To equip students with the developments, justifications, implementation, and use of representational,
formalism and search methods.
Aims & Objectives  To provide an opportunity to students to learn methods most useful under complex computational uncertain,
and vague situations.
 Enabling students to study advanced courses in the field such as machine learning, neural networks, text and
data
Learning Outcomes mining.
 Demonstrate the ability to apply AI and Computational Intelligence techniques to a variety of research and
application projects.
 Artificial Intelligence: A modern approach. Russell and Norvig, 3rd edition Pearson Education Series in AI
Text Book
 Luger, George & Stubblefield, William (2004), Artificial Intelligence: Structures and Strategies for Complex
Reference Books Problem Solving (5th ed.),
&  Mathematical Methods in Artificial Intelligence. (Edward A. Bender).
Material  Principals of Artificial Intelligence and Expert Systems Development. (David W. Rolston)
 Nils J Nilson, Artificial Intelligence – A New Synthesis, Morgan Kaufman Publishers, Elsevier, USA.
 Patrick Henry Winston, Artificial Intelligence, Third Edition, Pearson Education Series in AI.
Assignment(s): 10%
Grading Breakup and Quizzes: 5%
Policy Project: 10%
Midterm Examination: 25%
Final Examination: 50%
Collaboration and group work is encouraged but each student is required to submit his/her own contribution(s).
Plagiarism Policy: Your writings must be your own thoughts. Cheating and plagiarism will not be tolerated and will be referred to the
HoD & Dean for appropriate action(s).
Recommendations
for Learning
Activities
Source
Week# Lecture # TOPICS (Mention Assignments,
(Book, Chapter No)
Test, Case Study,
Projects, Lab Work or
Reading Assignments)
01 Introduction: History, Applications and Future A) Chapter 1

01
02 Intelligent Agents: Agents and environments, Rationality, Agent Types B) Chapter 2
02 03, 04 Knowledge Representation with AI applications: Propositional Logic, Predicate Calculus A) Chapter 2
Problem solving through Search Methods:
 Introductions
03 05,06  State Space Search A) Chapter 3
 Depth First Search
 Breath first search
Problem solving through informed search:
 Heuristically Informed Methods
04 07,08  Hill Climbing, Beam Search A) Chapter 3
 Best First Search A*Procedure
 Adversarial Search
A) Chapter 4,5
05 09,10  Min-Max Procedure
 Static Evaluation Function
 Alpha Beta Pruning
Expert systems: A) Chapter 7
11
Introduction to Expert Systems, Knowledge Base Expert System Their Types and Application,
06 Expert Systems:
A) Chapter 8,9
12 Working of Expert Systems with its different components, Typical examples, its benefits, the down side,
Developing an Expert System, Identifying the problem
Reasoning in uncertain situations:
 Crisp/ Classical Set Theory
 Fuzzy Set Theory A) Chapter 9
07 13,14
 Crisp Logic
 Fuzzy Logic
 Fuzzy System: Fuzzy Set Theory, Fuzzy Inference
Machine learning: symbol-based
Supervised Learning: Decision Tree A) Chapter 10
08 15,16
 Information Theory
Feature Selection
 Entropy
 Information Gain
Highly Branches Attribute
 Gain Ratio for Attribute Selection (C4.5)
Alternative to void selecting attributes with large-domain
 Gini Index
Mid Term Exam
Unsupervised learning:
Hierarchical
 Agglomerative
09 17,18  Divisive A) Chapter 10
Portioning
 K-Mean
 Clustering (KNN)
Reinforcement Learning:
10 19,20  Passive and Active Reinforcement Learning A) Chapter 10
 Q-Learning
Machine Learning: Connectionist
Neural Network:
A) Chapter 11
11 21,22  Introduction to Artificial Neural Networks (ANN), ANN Applications , Topologies of ANN,
 Single Layer perception (SLP)
 Numerical Example
Back Prop algorithms:
A) Chapter 12
12 23,24  Multi-Layer Perception (MLP),
 Back Prop Algorithm with Example
Machine Learning: Genetic and Emergent
 Introduction to Evolutionary Computing, Genetic Algorithm (GA)
A) Chapter 12
13 25,26  Applications of Genetic Algorithm and its examples , Genetic operators (Crosse over and Mutation)
and its applications ,
 Real World Numerical Example solved with G.A
Machine Learning: Genetic and Emergent
 Particle Swarm Optimization (PSO): Introduction to Swarm Intelligence (SI),
A) Chapter 12
14 27,28  Particle Swarm Optimization (PSO),
 Pseudo Code ,
 Real World Numerical Example solved with PSO
Machine Learning: Probabilistic
A) Chapter 13
15 29,30 Hidden Markov Models (HMMs),
 Joint Distribution of an HMM
 Chain Rule and HMM
 Filtering / Monitoring
Dynamic Bayesian Networks and Learning
 Support Vector Machine (SVM)
16 31,32  Advanced Topics in AI Handouts
o Deep Learning
Final Exam

CS - AI - 16 Weeks Plan

Uploaded by

Copyright:

Available Formats

CS - AI - 16 Weeks Plan

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CS - AI - 16 Weeks Plan

Uploaded by

Copyright:

Available Formats

Sixteen Week Plan

Department of Computer Science

Title Artificial Intelligence

01 Introduction: History, Applications and Future A) Chapter 1

You might also like