Practical

AI for Data Analysis: Learning and Deriving Value from Structured and Unstructured Data

The course provides the theoretical and practical foundations of the main data analysis and machine learning techniques. Advanced Deep Learning (DL) techniques are presented, offering an overview of models such as RNN (Recurrent Neural Networks), LSTM (Long Short-Term Memory), and an introduction to transformers.

CONTENT

Introduction to Deep Learning:
• Neural Networks.
• Loss function and training.
Data Preparation:
• Data cleaning and normalization.
• Data visualization techniques.
Machine Learning:
• Linear Regression.
• Logistic Regression.
• KNN (K-Nearest Neighbors) / SVM (Support Vector Machine) / PCA (Principal Component Analysis)/ K-Means.
Deep Learning
• RNN, LSTM.
• Introduction to Transformers.
Exercises

OBJECTIVES

The course aims to provide students with the necessary knowledge to apply the main Machine Learning and Deep Learning techniques to real datasets. Students will learn to implement regression, classification, and clustering algorithms, while gaining an overview of neural networks and how they are used for sequential data analysis.

LEARNING OUTCOMES

By the end of the course, students will be able to process, clean, and normalize data for analysis. They will learn to correctly choose and apply ML and DL algorithms, and receive an initial introduction to Transformers.

PREREQUISITES

Experience in Python programming.