https://github.com/imwrdo/artificial-intelligence

ML course on Gdansk University of Technology
https://github.com/imwrdo/artificial-intelligence

artificial-intelligence machine-learning pandas-python python3

Last synced: 3 months ago
JSON representation

ML course on Gdansk University of Technology

• Host: GitHub
• URL: https://github.com/imwrdo/artificial-intelligence
• Owner: imwrdo
• License: mit
• Created: 2024-03-14T18:46:31.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-05T18:07:46.000Z (about 1 year ago)
• Last Synced: 2024-04-05T20:25:20.972Z (about 1 year ago)
• Topics: artificial-intelligence, machine-learning, pandas-python, python3
• Language: Python
• Homepage:
• Size: 19.5 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Subject Title: Artificial intelligence

## About

This repository contains completed labs for the Artificial Intelligence course at my university.

The labs are designed to cover various topics within artificial intelligence,

providing hands-on experience and practical understanding of AI algorithms and machine learning techniques.

## Labs Description

1. Linear Regression

  - Description: This lab focuses on implementing and understanding the basics of linear regression, a fundamental technique in machine learning for predicting continuous values.This file implements simple linear regression to predict MPG (miles per gallon) using weight as the independent variable. It starts by obtaining and inspecting the data, followed by splitting it into training and testing sets. The closed-form solution is then computed to find the parameters that minimize the prediction error, with Mean Squared Error (MSE) used as the error metric. Additionally, it standardizes the data and calculates theta using Batch Gradient Descent, providing further analysis of the error and plotting the regression line for both the original and standardized data.

  - Folder: Lab1

  - Status: Completed and Published

2. Genetic Algorithm

  - Description: In this lab, we study genetic algorithms inspired by the process of natural selection and genetics. Genetic algorithms are used to solve optimization and search problems. In my case, the genetic algorithm solved the knapsack  problem

  - Folder: Lab2

  - Status: Completed and Published

3. Minimax and Alphabeta Algorithms

  - Description: This lab contains my implementation of the classic game Tic-Tac-Toe with artificial intelligence powered by two search algorithms: Minimax and Alpha-Beta Pruning. Developed as part of my university lab project, this program demonstrates the application of these algorithms in creating a challenging opponent for the game.

  - Folder: Lab3

  - Status: Completed and Published

4. Classification

  - Description: In our lab, we dive into the world of classification in Machine Learning, where data is categorized into predefined classes. Participants explore a variety of algorithms, from traditional ones like decision trees and support vector machines to cutting-edge deep learning techniques such as convolutional neural networks. Through hands-on experimentation and theoretical understanding, attendees gain insights into model evaluation, performance tuning, and the interpretability of classification results. Join us to unravel the intricacies of pattern recognition and its applications across diverse domains.

  - Folder: Lab4

  - Status: Completed and Published

5. Clusterisation

  - Description: This lab delves into the domain of cluster analysis, a fundamental technique in unsupervised learning aimed at grouping similar data points. Participants explore various clustering algorithms, such as K-means, hierarchical clustering, and DBSCAN, understanding their strengths, weaknesses, and applications. Through hands-on exercises, attendees gain practical experience in clustering real-world datasets, analyzing clusters' characteristics, and interpreting results. Join us to unravel the mysteries of unsupervised learning and discover how clustering algorithms can unveil hidden patterns within your data

  - Folder: Lab5

  - Status: Completed and Published

6. Artificial neural networks

  - Description: This lab is designed to provide hands-on experience with the fundamental concepts and advanced techniques of ANNs. We are exploring the architecture, training methods, and applications of neural networks, from simple perceptrons to deep learning models. Through a series of practical exercises and projects, we are gaining a solid understanding of how ANNs can be utilized to solve complex problems in various domains such as image recognition, natural language processing, and predictive analytics.

  - Folder: Lab6

  - Status: In progress