Skip to content

Latest commit

 

History

127 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

University of Windsor

Computational Intelligence

ELEC 8330 · Semester IV · MEng Computer Engineering

License: CC BY 4.0 University Program Curated by

A comprehensive academic archive for Computational Intelligence (ELEC 8330), documenting technical proficiency in neural architectures, fuzzy logic systems, evolutionary computing, and intelligent optimization standards within the Master of Engineering program.


Overview  ·  Contents  ·  Reference Books  ·  Personal Preparation  ·  Assignments  ·  MATLAB Programs  ·  Examinations  ·  Grades  ·  Syllabus  ·  Usage Guidelines  ·  License  ·  About  ·  Acknowledgments


Overview

Computational Intelligence (ELEC 8330) is a specialized graduate-level course in the Master of Engineering (MEng) program at the University of Windsor. This course focuses on the exploration and implementation of advanced intelligent systems, encompassing neural networks, fuzzy logic, and genetic optimization for solving complex engineering paradigms.

Course Objectives

The curriculum encompasses several key intelligent computing domains:

  • Neural Networks: Mastering Hebbian learning, Associative Memories (AM), and Bidirectional Associative Memories (BAM).
  • Self-Organizing Maps: Implementing competitive learning via SOM and Learning Vector Quantization (LVQ) architectures.
  • Fuzzy Systems: Developing fuzzy set theory, reasoning models, and high-fidelity inference systems.
  • Genetic Optimization: Leveraging evolutionary algorithms for global search and multi-objective optimization.
  • Intelligent Modeling: Utilizing Radial Basis Function (RBF) networks and Convolutional Neural Networks (CNNs) for predictive analysis.

Repository Purpose

This repository represents a curated collection of study materials, reference books, course assessments, and technical implementations compiled during my academic journey. The primary motivation for creating and maintaining this archive is simple yet profound: to preserve knowledge for continuous learning and future reference.

As I progress in my career, I recognize that the foundations of computational intelligence remain essential for solving complex engineering problems and explaining them with technical precision. This repository serves as my intellectual reference point: a resource I can return to for relearning concepts, reviewing methodologies, and strengthening understanding when needed.

Why this repository exists:

  • Knowledge Preservation: To maintain organized access to comprehensive study materials beyond the classroom.
  • Continuous Learning: To support lifelong learning by enabling easy revisitation of fundamental intelligent principles.
  • Academic Documentation: To authentically document my learning journey through Computational Intelligence.
  • Community Contribution: To share these resources with students and learners who may benefit from them.

Note

All materials were created, compiled, and organized by me during the Winter 2024 semester as part of my MEng degree requirements.


Repository Contents

Reference Books

This collection includes comprehensive reference materials covering all major topics:

# Resource Focus Area
1 Intelligent Computing - Hon K. Kwan Core textbook for advanced AI paradigms and neural computation.
2 Worked Problems in Intelligent Computing Practical exercise suite and MATLAB-integrated problem-solving.

Personal Preparation

Academic roadmap and administrative records for the Winter 2024 session:

# Resource Description
1 Course Syllabus Official course outcomes and assessment specifications
2 MEng Class Schedule Enrollment record and pedagogical timeline
3 Midterm Exam Revision Targeted theoretical synthesis for midterm evaluation

Assignments

A granular record of analytical assessments and tactical computational proofs conducted during the Winter 2024 session.

# Assignment Topics Source Code Report Marks
1 AM Quiz Associative Memories (AM) View 1 / 1
2 Assignment 1 Associative Memories (AM/BAM) BAM & Hopfield Q1A & Q1B 1 / 3
3 Assignment 2 Self-Organizing Maps (SOM) SOM Q1 4 / 4
4 Assignment 3 Learning Vector Quantization (LVQ) LVQ Q1 3 / 3
5 Assignment 4 Radial Basis Function (RBF) RBF & Optimization Q1 3 / 3
6 Assignment 5 Fuzzy Sets (FSet) FSet Q1 4 / 4
7 Assignment 6 Fuzzy Logic and Reasoning (FLR) Q2a & Q2b 4 / 4
8 Assignment 7 Fuzzy Systems (FSys) Q2a & Q2b 4 / 4
9 Assignment 8 Genetic Algorithms (GA) GA Q1 & Q2 0 / 4
10 Assignment 9 Convolutional Neural Networks (CNNs) Q1 2 / 2

MATLAB Programs

Technical solutions and algorithmic models developed to implement neural networks, fuzzy logic, and genetic algorithms.

Programs Language Status Developed by

Tip

Computational Intelligence is not merely the execution of algorithms; it is the practical application of heuristics to simulate intelligent behavior. These technical implementations focus on functional problem-solving through computational modeling, providing a reliable framework for the rigorous design and verification of intelligent systems.

# Topic Source Code
1 Binary to Decimal Conversion (Util) View
2 Decimal to Binary Conversion (Util) View
3 Fuzzy Set Theory Operations (FSet) View
4 Fuzzy Set Theory (FSet) View
5 Fuzzy Logic and Reasoning (FLR) View
6 Fuzzy Reasoning System (FSys) View
7 Generalized Hopfield Network (AM) View
8 Bidirectional Associative Memory (AM) View
9 Learning Vector Quantization (LVQ) View
10 Self-Organizing Maps (SOM) View
11 Radial Basis Function Network (RBF) View
12 Radial Basis Function Optimization (RBF) View
13 Convolutional Neural Network (CNN) View
14 Genetic Algorithm Implementation (GA) View
15 Genetic Algorithm Optimization (GA) View
16 Genetic Algorithm Variant I (GA) View
17 Genetic Algorithm Variant II (GA) View

Examinations

The following examinations represent key assessment milestones in Computational Intelligence, documenting technical proficiency through mid-term evaluations and the final summative assessment.

Graduate Examination Records

# Examination Milestone Date Archival Deliverables Marks
1 Midterm Examination February 28, 2024 Midterm Revision Notes — by Amey Thakur
Q2A & Q2B Associative Memories Answer Sheet
Q2A Radial Basis Function Answer Sheet
Q2B Radial Basis Function Answer Sheet
Q2 Self-Organizing Maps Answer Sheet
15 / 24
2 Final Examination April 15, 2024 Fuzzy Set Theory — MATLAB Program
Q2A Fuzzy Sets Answer Sheet
Q2B Fuzzy Sets Answer Sheet

Genetic Algorithm Optimization — MATLAB Program
Q2A Genetic Algorithms Answer Sheet
Q2B Genetic Algorithms Answer Sheet

Fuzzy Logic and Reasoning — MATLAB Program
Q2A Fuzzy Logic and Reasoning Answer Sheet
Q2B Fuzzy Logic and Reasoning Answer Sheet

Fuzzy Reasoning System — MATLAB Program
Q2A Fuzzy Systems Answer Sheet
Q2B Fuzzy Systems Answer Sheet

Convolutional Neural Network — MATLAB Program
Q3A Convolutional Neural Networks Answer Sheet
Q3B Convolutional Neural Networks Answer Sheet
29 / 44

Grades

The graded performance record documents academic achievement across various assessment categories including assignments, midterm evaluations, and the final examination.

# Assessment Category Marks Archival Record
1 Final Grades 80 / 100 (80%) View Grades

Syllabus

Official ELEC 8330 Syllabus
Complete graduate-level syllabus document for the Winter 2024 session, including detailed course outcomes, theoretical modules, and assessment criteria for Computational Intelligence.

Important

Always verify the latest syllabus details with the official University of Windsor academic portal, as curriculum specifications for Computational Intelligence may undergo instructor-led adaptations across different sessions.


Usage Guidelines

This repository is openly shared to support learning and knowledge exchange across the academic community.

For Students
Use these resources as templates for MATLAB scripting in intelligent systems, reference materials for fuzzy reasoning, and examples of evolutionary optimization. All content is organized to support self-paced learning.

For Educators
These materials may serve as curriculum references, technical benchmarks for neural architecture, or supplementary instructional content in computational intelligence. Attribution is appreciated when utilizing content.

For Researchers
The simulations and algorithmic implementations may provide insights into scholarly Computational Intelligence patterns and graduate-level intelligent systems documentation.


License

This repository and all linked academic content are made available under the Creative Commons Attribution 4.0 International License (CC BY 4.0). See the LICENSE file for complete terms.

Note

Summary: You are free to share and adapt this content for any purpose, even commercially, as long as you provide appropriate attribution to the original author.


About This Repository

Created & Maintained by: Amey Thakur
Academic Journey: Master of Engineering in Computer Engineering (2023-2024)
Institution: University of Windsor, Windsor, Ontario
Faculty: Faculty of Engineering

This repository represents a comprehensive collection of study materials, reference books, technical assignments, and personal preparation notes curated during my academic journey. All content has been carefully organized and documented to serve as a valuable resource for students pursuing Computational Intelligence.

Connect: GitHub  ·  LinkedIn  ·  ORCID

Acknowledgments

Grateful acknowledgment to Dr. Hon Kwan for his exceptional instruction in Computational Intelligence, which played a pivotal role in shaping my analytical understanding of the subject. His clear and disciplined approach, along with his thorough explanation of neural networks, fuzzy logic, and genetic algorithms, made the subject both accessible and engaging. His distinguished expertise and commitment to academic excellence in Computational Intelligence are sincerely appreciated.

Grateful acknowledgment to Archit Konde for his outstanding understanding and distinguished peer mentorship. His exceptional ability to explain complex concepts with clarity and precision significantly enhanced my learning experience throughout the Computational Intelligence course. His dedication to academic excellence and scholarly support was fundamental to my mastery of advanced intelligent architectures and conceptual development.

Special thanks to the mentors and peers whose encouragement, discussions, and support contributed meaningfully to this learning experience.



Computer Engineering (M.Eng.) - University of Windsor

Semester-wise curriculum, laboratories, projects, and academic notes.