Ciencia de Datos

CPE Lyon

Academic Year 2025-2026

Starting from raw data, discover interesting patterns through supervised approaches (classification, regression) and unsupervised approaches (clustering, anomaly detection). Build on classical data mining foundations and progress to neural networks and deep learning. This course is part of the EL BONGO project.
PATTERN DISCOVERY

Course Overview

Syllabus

Course Content & Structure

Complete syllabus outlining all topics covered in this course.

View Course Plan

Course Materials

Classical Data Mining

Data Mining: Patterns & Algorithms

Data representation, classification (SVM, k-NN, Decision Trees, Random Forests), regression, clustering (K-Means, DBSCAN), anomaly detection, feature selection, and ML workflow best practices.

View Course
Neural Networks & Deep Learning

Neural Networks & Deep Learning

From perceptron to deep networks: MLP, activation functions, SGD/Adam optimisation, training stability, CNNs, scientific data modalities, uncertainty estimation, and ethics.

View Course

Practical Sessions

GitHub Repository

DataMining Repository

Comprehensive collection of practical exercises implementing data mining algorithms, pattern recognition projects, neural network applications, and real-world datasets.

Access on GitHub