Skip to content

Mathematics for Machine Learning Course (2023-I) Universidad Nacional de Colombia

License

Notifications You must be signed in to change notification settings

edserranoc/Mathematics_for_Machine_Learning_Course

Repository files navigation

Mathematics for Machine Learning

This repository contains the assignments for the "Mathematics of Machine Learning Course (2023-I)" given by Francisco A. Gómez J at Universidad Nacional de Colombia - Sede Bogotá, developed in the Python language.

1. Binary Classification

This folder contains a practical application of machine learning using the Banknote Authentication and Occupancy Detection Data Sets. The goal is to classify the data into two categories using various machine learning models, including SVM, KNN, logistic regression, and Decision Tree Classifier. The models are compared using various metrics to determine the best approach.

2. EigenFaces - Data Representation

The objective of this folder is to address topics related to dimensionality reduction and data representation. The algorithm implemented for dimensionality reduction is Principal Component Analysis (PCA), which is used to find the faces that better represent a dataset of face images. Finally, we search for the eigenfaces that are most relevant in representing an image of my own face.

3. Learning From Data Exercises

The objective of this folder is to solve some of the exercises from the book Learning From Data - by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, Hsuan-Tien Lin.


Link Recommendations

[1] A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras, and TensorFlow 2. GitHub Repository, Aurélien Geron Handson-ml3.
[2] Learning From Data: Professor Yaser Abu-Mostafa.

License

This project is licensed under the Apache-2.0 license. See the LICENSE file for details.

About

Mathematics for Machine Learning Course (2023-I) Universidad Nacional de Colombia

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published