Aprendizagem Profunda
pt
en
Planeamento
Não existe planeamento de aulas.
Página Inicial
Grupos
Avaliação
Bibliografia
Horário
Métodos de Avaliação
Objectivos
Planeamento
Programa
Turnos
Anúncios
Sumários
Prérequisitos
Componente Laboratorial
Componente de Programação e Computação
Competências Transversais
Princípios Éticos
Notas
Resultado dos QUC
Horários de dúvidas
Theoretical lectures
Lecture 1 - Introduction
Lecture 2 - Machine Learning Basics
Lecture 3 - Linear Models I
Lecture 4 - Linear Models II
Lecture 5 - Neural Networks I
Lecture 6 - Neural Networks II
Lecture 7 - Representation Learning
Lecture 8 - Convolutional Neural Networks
Lecture 9 - Recurrent Neural Networks
Lecture 10 - Sequence-to-Sequence Models
Lecture 11 - Attention Mechanisms and Transformers
Lecture 12 - Large Pretrained Models
Lecture 13 - Deep Generative Models
Lecture 14 - Interpretability and Fairness
Practical Lectures
Lecture 1 - Introduction to Python and NumPy
Lecture 2 - Perceptron
Lecture 3 - Linear and Logistic Regression
Lecture 4 - Neural Networks and Backpropagation
Lecture 5 - Introduction to Pytorch
Lecture 6 - Q&A about HW1
Lecture 7 - PCA and Auto-Encoders
Lecture 8 - Convolutional Neural Networks
Lecture 9 - Recurrent Neural Networks
Lecture 10 - Attention Mechanisms
Lecture 11 - Q&A about HW2
Lecture 12: Word Embeddings and Large Pretrained Models
Homework Assignment #1
Homework Assignment #2
Remote Exam
Grades
Exam solutions