Homeworks of meta-heuristic algorithm course

This collection includes implementations of several algorithms created from scratch, including Ant Colony Optimization (ACO), Genetic Algorithm (GA) for Traveling Salesman Problem (TSP), Memetic Algorithm, Multi-Layer Perceptron (MLP), Neural Network, Particle Swarm Optimization (PSO), Simulated Annealing, and Self-Organizing Maps (SOM) for unsupervised learning.
You can see the project code along with the work report on GitHub.

This repository contains implementations of various algorithms from scratch:

  • Ant-Colony Optimization (scratch) This project presents a ground-up implementation of the Ant Colony Optimization (ACO) algorithm, a powerful optimization technique inspired by the foraging behavior of ants. Explore the code to understand how ACO is applied to solve complex optimization problems.
  • Genetic Algorithm Travelling Salesman Problem (scratch) In this project, I’ve crafted a Genetic Algorithm (GA) from the ground up to tackle the classic Traveling Salesman Problem (TSP). This repository showcases the development of the GA and its application to efficiently find optimal routes for the TSP.
  • Memetic Algorithm (scratch) This project provides insights into the creation and fine-tuning of a Memetic Algorithm, a hybrid optimization technique that combines the power of Genetic Algorithms and local search methods.
  • Multi Layer Perceptron (scratch) Explore the fundamentals of neural networks by building a Multi-Layer Perceptron (MLP) model from scratch. This project demonstrates how to construct a neural network architecture, train it, and use it for various tasks.
  • Neural-Network (scratch) Starting from scratch, it walks you through the construction of a neural network, explaining each component and demonstrating its application in solving real-world problems.
  • Particle-Swarm Optimization (scratch) PSO is a bio-inspired optimization technique, and this project demonstrates how it can be crafted from scratch to solve complex optimization challenges.
  • Simulated Annealing (scratch) Simulated Annealing is a powerful optimization algorithm, and this project presents a step-by-step development of the algorithm from scratch. You can explore the code and gain a deep understanding of how Simulated Annealing works to find global optima in complex landscapes.
  • SOM (scratch) Self-Organizing Maps (SOMs) are a fascinating neural network architecture for unsupervised learning. This project provides an in-depth look into SOMs by developing one from scratch. Explore the code to understand how SOMs organize and visualize data in a two-dimensional map.

In this lesson, to solve one of the problems raised, I prepared a code and PowerPoint and presented it in class.

Leave a Comment