Deep Learning

Objectives

N/A

General characterization

Code

200180

Credits

3.5

Responsible teacher

Mauro Castelli

Hours

Weekly - Available soon

Total - Available soon

Teaching language

Portuguese. If there are Erasmus students, classes will be taught in English

Prerequisites

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)

Bibliography

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

Teaching method

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 only 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.

Evaluation method

English

Subject matter

Theoretical and practical classes.

Programs

Programs where the course is taught: