Aprendizagem Profunda

Objectivos

- Understand the design principles of neural networks;

- Understand the concept of activation function;

- Understand the backpropagation algorithm for training a neural network;

- Being able to build a neural network to solve classification tasks;

- Being able to use Keras or similar libraries to build a Neural Network;

- Understand the convolution operator and the idea behind convolutional neural network;

- Understand the main principles of recurrent neural network; 

- Understand LSTM and how they can be applied to counteract vanishing gradient problem.

- Being able to apply one of the deep model presented to solve classification or regression tasks.

Caracterização geral

Código

200180

Créditos

3.5

Professor responsável

Mauro Castelli

Horas

Semanais - A disponibilizar brevemente

Totais - A disponibilizar brevemente

Idioma de ensino

Português. No caso de existirem alunos de Erasmus, as aulas serão leccionadas em Inglês

Pré-requisitos

N/A

Bibliografia

Deep Learning. Ian Goodfellow, Yoshua Bengio, Aaron Courville. MIT Press, 2016.

Método de ensino

Theoretical and practical classes.

Método de avaliação

First epoch: deep learning project.

Second epoch: deep learning project.

Conteúdo

Introduction to deep learning

History and cognitive basis of neural computation.

The perceptron / multi-layer perceptron

The neural net as a universal approximator

Optimization by gradient descent

Back propagation

Overfitting and regularization (Dropout)

Convolutional Neural Networks (CNNs)

Training with shared parameters: the convlutional model

Recurrent Neural Networks (RNNs)

Exploding/vanishing gradients Long Short-Term Memory Units (LSTMs)

Cursos

Cursos onde a unidade curricular é leccionada: