Aprendizagem Profunda

By the end of this course, students will:

· Understand the core concepts, paradigms, and challenges of DL.

· Understand the theoretical foundations of DL, such as backpropagation, optimization, and activation functions.

· Know the advantages and limitations of DL models and their applications.

· Be able to implement and optimize DL algorithms using frameworks like PyTorch.

· Be able to experimentally model data using the explored architectures.

· Be able to analyze and evaluate model performance using metrics and visualizations.

· Be able to compare and validate different DL approaches for diverse datasets.

· Be able to assess the suitability of deep learning methods for various domains.

· Be able to critically evaluate results, addressing biases and ethical concerns.

• Be able to show autonomy in learning and applying DL advancements.