Advanced Machine Learning

Recommended Prerequisites

NA

Teaching Methods

During the lectures (T) the concepts, the theories, the algorithms will be presented and discussed. In the (PL) classes students will consolidate what was learned in T. The practical work will be done under the supervision of the teacher. Grading will be based on two components: (1) projects involving the techniques and/or a practical problem; (2) a written exam to assess students' knowledge about the subject of Advanced Machine Learning.

Learning Outcomes

After completing the curricular unit, it is expected that students acquire knowledge about advanced topics of computational learning and skills for the development of solutions involving: deep learning networks, generative models and reinforcement learning models. In the end, they should be able to analyze, model, implement, train and execute: - fully connected, convolutional, sequential and recursive networks of graphs and "transformers" - autoencoders, variational autoencoders, generative adversarial networks and diffusion models - model free q-learning and deep q-networks. Students will consolidate their communication skills, analysis and synthesis, writing and speaking, and of working in group.

Work Placement(s)

No

Syllabus

1. Model Training 1.1 Forward Propagation 1.2 Backpropagation and Chain Rule 1.3 Optimization and Optimizers 1.4 Initialization, Normalization and Regularization 2. Deep Learning 2.1 Deep Neural Networks 2.2 Convolutional Neural Networks 2.3. Sequence Models and Recurrent Neural Networks 2.4. Graph Neural Networks 2.5. Transformers 3. Generative Machine Learning 3.1 Autoencoders 3.2 Variational Autoencoders 3.3 Generative Adversarial Networks 3.4 Diffusion Models 4. Reinforcement Learning 4.1 State Machines 4.2 Markov Decision Process 4.3 Sate of Environment and Agents 4.4 Policy, State Actions and Reward Functions 4.5 Q-Learning 4.6 Deep Q-Networks

Head Lecturer(s)

Nuno António Marques Lourenço

Assessment Methods

Assessment
Exam: 50.0%
Project: 50.0%

Bibliography

1. Iddo Drori (2022) The Science of Deep Learning (1st Edition), Cambridge University Press 2. Ethem Alpaydin (2010), Introduction to Machine Learning (2nd Edition), MIT Press 3. Richard S. Sutton and Andrew G. Barto (2018), Reinforcement Learning: an introduction (2nd Edition), MIT Press 4. Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016), Deep Learning, MIT Press