Name: Santiago Ahumada L
Type: User
Company: Universidad Nacional de Colombia
Bio: Maths Student | ML & Data Science
Twitter: sahumadaloz
Location: Bogotá, Colombia
Blog: https://santiagoal.super.site/
Santiago Ahumada L's Projects
Aprendizaje automático en la celebración de contratos gubernamentales en Colombia.
Machine Learning model API deployed with GCP & DVC. Predicts a breast-cancer diagnostic.
In this repository I am gonna show the main and most popular non-supervised clustering algorithms with short explanations.
In this repository I'm going to implement a machine learning clustering algorithm in order to recognize handwritten digits
Dogs Vs Cats is a CNN based model. Its purpose is to classify a images dataset into two classes: Cats and Dogs.
Here you can put your own alphabet and the transition diagram, then, the automata will recognize only the accepted strings.
Here we will consign interesting stuff about Julia programming language
DeepGlobe LandCover Satellite Image Segmentation Challenge
Coursework for the assignment Machine Learning 2023-I
Here are the homeworks of the assignature Introduction to Machine Learning of my maths degree
¡Hello there! In this repository I am supposed to show the main components of my own programming language (LLP). Its lexer within a parser,(which generates abstract syntax trees), but also an inner object representation and a REPL evaluator.
This is the final project of the assignature numerical analysis which obtained a hight grade.
A computer vision model using a pre-trained model from the hugging face hub. It classifies beans' photos by its quality.
Image classification using a CNN architecture.
Unsupervised Learning used to group countries' data.
Unsupervised learning algorithms built to make costumer segmentation. Clustering is implemented with DBSCAN. We made data preprocessing with PCA.
Main visualization tools in python.
Here we built a multinomial logistic regression classifier with scikit-learn. It takes numerical data of a bean an predicts which class does it belong to.