Deep Learning Methods in Finance

Objetivos

Present the area of deep learning. Discuss different architectures and the guidelines for building a deep learning neural network. Be able to implement and train a neural network in Keras.

Caracterização geral

Código

400107

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

NA

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.

The project is the same for the two epochs. The student can defend the project in one of the two epochs.

If a student fails the first epoch he/she is responsible for proposing a new project that must be validated by the professor.

The same applies to students that want to improve the grade.

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)

Cursos

Cursos onde a unidade curricular é leccionada: