Introduction to Machine Learning

Overview

This training program equips students with the ability to formulate and structure machine learning problems based on real-world needs, distinguishing between prediction, classification, and clustering tasks, and selecting the most appropriate data, features, and metrics for each case. Participants will learn to prepare, process, and model datasets using tools from the Python ecosystem, developing reproducible pipelines with pandas and scikit-learn, and applying basic supervised and unsupervised models. Finally, they will develop skills in evaluating, interpreting, and communicating modeling results using appropriate metrics, as well as deploying lightweight inference prototypes with Streamlit or Gradio to practically demonstrate the utility and applicability of the constructed model.

Goals

Acquire skills to formulate and structure machine learning problems (prediction, classification and grouping) based on real needs, identifying the appropriate data and metrics.
Prepare, process, and model datasets using Python tools, building reproducible pipelines with pandas and scikit-learn, and applying basic supervised and unsupervised models.
Evaluate, interpret and communicate results using appropriate metrics and deploying lightweight inference prototypes (Streamlit or Gradio) that demonstrate the applicability of the model.

Access requirements

Academic program

If you do not hold a bachelor's degree, students enrolled in undergraduate or master's degree programs will be accepted, preferably those in the fields of Engineering and Architecture and Science, as these provide the necessary technical and analytical foundation for understanding the course content. Undergraduate degrees at the University of La Laguna considered particularly relevant include:

Engineering and Architecture Branch

Bachelor's Degree in Computer Engineering
Bachelor's Degree in Industrial Electronics and Automation Engineering
Bachelor's Degree in Mechanical Engineering
Bachelor's Degree in Industrial Chemical Engineering
Bachelor's Degree in Civil Engineering
Degree in Technical Architecture
Bachelor's Degree in Marine Technologies
Degree in Nautical Studies and Maritime Transport

Branch of Sciences

Bachelor's Degree in Mathematics
Bachelor's Degree in Physics
Bachelor's Degree in Chemistry
Bachelor's Degree in Biology
Bachelor's Degree in Environmental Sciences

Students and graduates from other fields of knowledge, such as Social Sciences and Law, Health Sciences or Arts and Humanities, may also be admitted, provided they demonstrate interest or experience in areas related to technology, data analysis, programming or digital innovation.

Academic program

Contents

Block 0: Getting Started and ML Mindset

Introduction to the working environment: installation of Python 3.11+, main libraries (pandas, scikit-learn).
Version control and best practices with Git and GitHub
Typical structure of a machine learning project.
Creating a dataset card to document the data.

Block 1: Data and Exploratory Data Analysis (EDA)

Data cleaning and debugging
Imputation of missing values and handling of outliners
Lightweight variable engineering
Exploratory visualization (distributions, correlations, key relationships)

Block 2: Supervised Learning I

Basic models: linear regression, logistic regression, and decision trees
Baseline creation and comparison of initial models
Regulation and control of overfitting
Interpretation of coefficients and rules

Block 3: Unsupervised Learning

Clustering algorithms: k-means, DBSCAN
Dimensionality reduction: PCA, UMAP
Internal evaluation metrics (silhouette, Davies-Bouldin)
Typical use cases: customer segmentation, anomaly detection, data compression.

Block 4: Evaluation and Validation

Data separation: train/validation/test split, cross-validation (k-fold)
Time series validation and management.
Main Metrics: MAE, RMSE, Accuracy, F1, PR-AUC
Thresholding adjustment and decision optimization.

Block 5: Integrative Project

Formulation of a complete practical case of machine learning.
Development of an end-to-end pipeline (data -> model -> inference)
Preparation of technical report and visualization of results.

Methodology and activities

– Exhibitions, debates and presentation of works and projects: activities supervised by the teaching staff.

– Active methodologies: cooperative learning, project-based learning, flipped classroom, service learning, game-based learning, case studies, problem solving aimed at making learning a participatory process.

Evaluation criteria

Based on the following assessment tests:

– Objective tests (true/false, multiple choice, test-type, fill-in-the-blank, ordering, etc.) that will allow the evaluation of knowledge, skills, performance, aptitudes, etc. The answers will be closed-ended, and objectivity will be favored during the marking process.

– Case, exercise and problem solving: tests in which students must solve, in a reasoned manner, within a certain time, and according to the established criteria, the cases, exercises or problems posed by the teaching staff, with the aim of applying the knowledge acquired.

– Works, memoirs, internship reports, written reports and projects: documents prepared on a topic or activity carried out, following the instructions established by the teaching staff.

– Oral presentation and defense of topics, works, etc.

General information

Credits: 2 ECTS

Duration: 26/12/2025-16/01/2026

Teaching modality: In-person/Online/Hybrid

Location: Virtual Classroom/Higher School of Engineering and Technology

Registration

Flexibility

Short courses available in various formats (in-person, online, or hybrid). Ideal for learning without interrupting your professional life.

Employability

Content created and delivered by professionals and experts in the field, designed for immediate application.

Certification

Endorsed by the University of La Laguna. You will receive an official ECTS certificate, valid in the European Higher Education Area.

Teaching staff

Pino Teresa Caballero Gil

Professor at the University of La Laguna, with a degree in Mathematics and a PhD in Statistics, Operations Research and Computing. She teaches in the Department of Computer Engineering and Systems in the area of Computer Science and Artificial Intelligence and is head of the CryptULL research group and the ULL's Cryptology research group.

Marcos Rodríguez Vega

Hired for a Research Project at the University of La Laguna

Tuition

Registration link

Registration

Registration fee with or without discount: €50. Price per credit: €25

Tuition fees subsidized by the Cybersecurity Chair of the University of La Laguna C065/23, financed by the National Cybersecurity Institute (INCIBE) and funds from the Recovery, Transformation and Resilience Plan – Next Generation EU funds

Introduction to Machine Learning