Aprendizagem com Dados Não Estruturados

At the end of this unit, students will:

Understand:
-Basic principles of deep learning.
-Unsupervised extraction of features and learned representations for use in regression or classification in multi-layer models.
-Optimization and regularization methods applicable to models with a large number of parameters
-The different models presented: fully connected feed-forward neural networks, convolution networks, and recurrent networks.
-Problems and techniques for processing unstructured data.

Be able to:
Select and implement models to solve some typical problems and optimize training to obtain a reasonable solution

Know:
Problems solvable with deep learning: object recognition in images, voice recognition, natural language processing, and others.