Skip to content

A hands-on collection of 9 projects exploring neural networks, fuzzy logic, and genetic algorithms, designed to apply computational intelligence to real-world problems with full implementations and thoughtful evaluations.

Notifications You must be signed in to change notification settings

ImRanjbar/Computational-Intelligence-Projects

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Computational Intelligence Projects

Implementation and analysis of computational intelligence methodologies across neural networks, fuzzy logic systems, and genetic algorithms, featuring 9 complete projects with systematic evaluation.

Repository Structure

1. Genetic Algorithm

Directory: Genetic_Algorithm/
1 Project: Evolutionary computation for optimization

  1. Genetic Algorithm for Feature Selection - Customer classification optimization

2. Fuzzy Logic Systems

Directory: Fuzzy_Logic_Systems/
3 Projects: Intelligent fuzzy inference systems for real-world applications

  1. Intelligent Fitness Recommendation System - Personalized workout optimization
  2. Fuzzy Logic Irrigation Control Systems - Environmental decision making
  3. Intelligent Fuzzy Student Performance Prediction - Academic outcome prediction with ML pipeline

3. Deep Learning Neural Networks

Directory: Deep_Learning_Neural_Networks/
5 Projects: Progressive neural network implementations using CIFAR-10 dataset

  1. Logistic Regression from Scratch - Binary classification with pure NumPy
  2. Single Hidden Layer Neural Network - Basic neural network fundamentals
  3. Multi-Class Neural Network - Complete CIFAR-10 classification
  4. Deep Neural Network Framework - Modular framework with multiple optimizers
  5. CNN Architecture Comparison - Advanced convolutional networks with regularization

Methodology & Technologies

  • Neural Networks: From-scratch implementations (NumPy) and framework-based solutions (TensorFlow/Keras)
  • Fuzzy Logic: scikit-fuzzy implementations with interactive decision interfaces
  • Genetic Algorithms: Custom evolutionary optimization with fitness-based selection
  • Evaluation: Performance analysis across classification accuracy, optimization convergence, and decision quality metrics

Requirements

pip install numpy pandas matplotlib seaborn scikit-learn tensorflow scikit-fuzzy gradio

Contributors

Course Information

Course: Computational Intelligence
University: University of Isfahan
Professor: Dr. Hossein Karshenas
Semester: Spring 2025

About

A hands-on collection of 9 projects exploring neural networks, fuzzy logic, and genetic algorithms, designed to apply computational intelligence to real-world problems with full implementations and thoughtful evaluations.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published