An introduction to Machine Learning
This session introduces participants to the core concepts of Machine Learning (ML) and demonstrates how to use different Python Integrated Development Environments (IDEs) effectively within ML workflows.
10h00 – 12h00: Theory (1h30) + Q&A (30min)
14h30 – 16h30: Practical session (2h) – Introduction to simple models, examples, and exercises.
This session introduces participants to the core concepts of Machine Learning (ML) and demonstrates how to use different Python Integrated Development Environments (IDEs) effectively within ML workflows. Through a combination of theory and practice, participants will gain both conceptual understanding and hands-on experience applying ML techniques.
By the end of the session, participants will be able to:
1) Understand the fundamental principles of Machine Learning.
2) Learn about the different phases and types of ML models.
3) Gain insights into Convolutional Neural Networks (CNNs) and Gaussian Processes, including their mathematical foundations and real-world applications.
4) Get hands-on experience using two popular Python IDEs for ML development.
b) Session Topics
1) Introduction to Machine Learning (ML)
1.1) What is ML, and why does it matter today?
1.2) Key applications in various industries.
2) Phases of a Machine Learning Project
2.1) Data collection, preprocessing, model training, evaluation, and deployment.
3) Types of Machine Learning and When to Use Each
3.1) Supervised, Unsupervised, and Reinforcement Learning.
4) Convolutional Neural Networks (CNNs)
4.1) Mathematical foundations and intuition.
4.2) Real-world examples and use cases.
5) Gaussian Processes
5.1) Mathematical background and theoretical understanding.
5.2) Practical examples and applications.
6) Group Exercise
6.1) Collaborative task in pairs to apply learnt concepts to a practical ML problem.
Dinamizador(es):
João Pedro da Silva Moreira dos Santos