Machine Learning Labs

This repository contains a collection of Jupyter notebooks developed as part of the Machine Learning course for the Master's Degree in Computer Engineering at the University of Florence.

📂 Repository Contents

The repository includes the following notebooks, each focused on a specific topic in machine learning:

1. Linear Regression.ipynb:

   • Introduction to linear regression.
   • Practical implementations using NumPy and scikit-learn.
   • Applications to predictive modeling.

2. Classification.ipynb:

   • Supervised classification techniques.
   • Logistic regression and Support Vector Machines (SVM).
   • Model evaluation and metrics.

3. Convolutional Neural Networks.ipynb:

   • Designing and training Convolutional Neural Networks (CNNs).
   • Image recognition tasks using PyTorch.
   • Discussion of CNN architectures.

4. Unsupervised Learning.ipynb:

   • Methods for unsupervised learning, including:
     • Clustering (k-means).
     • Dimensionality reduction (Principal Component Analysis - PCA).
   • Exploratory data analysis applications.

5. Pytorch Lab.ipynb:

   • Hands-on exercises with PyTorch.
   • Building and training deep learning models.
   • Understanding tensors and backpropagation.