Skip to content

dvPineda/Bioinspired-Algorithms-ELM-Training

Repository files navigation

DEVELOPMENT OF BIO-INSPIRED ALGORITHMS FOR THE TRAINING OF ELM NEURAL NETWORKS 🧠

📖 Overview

This project focuses on the development and optimization of Extreme Learning Machine (ELM) neural networks. The aim is to enhance the model's fitness and precision by implementing different bio-inspired algorithms between the input and hidden layer. These algorithms are used to optimize the weights and biases, as well as perform feature selection.

🚀 Bio-Inspired Algorithms

The project implements three different bio-inspired algorithms:

  1. Genetic Algorithm (GA) 🧬
  2. Particle Swarm Optimization (PSO) 🐦
  3. Coral Reef Optimization (CRO) 🐠

The CRO-ELM is a novel approach proposed in this project, aiming to improve the current state-of-the-art.

⚠️ Restrictions

Per the author and tutor's instructions, the implementation of the neural networks and the formulas must be done from scratch. The use of any external libraries like Tensorflow or Keras for these implementations is strictly prohibited.

📄 Final Project Report

You can access the final project report here.

🎥 Final Presentation

For more details about the project, please refer to the Final Presentation.

🔮 Future Work

This project serves as a stepping stone towards more advanced and efficient bio-inspired algorithms for neural network training. Future work will focus on refining these algorithms and exploring their applications in various domains.

About

Repository for my Final Degree Project

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published