Análise de Dados

Basic knowledge of intelligent data analysis.

Basic knowledge of Python.

Theoretical classes: Presentation of new concepts and discussion of examples.

Practical classes: Implementation and testing of data analysis models for concrete problems

The main objective of the Data Analysis course is to present a set of techniques and methodologies based on
deep neural networks to solve real data analysis problems. Understanding the potential of these systems
and the ability to develop architectures with these characteristics will give students a set of specialized skills
to work in the area of computational data analysis. The main learning objectives of this course are:

1. Know and understand advanced concepts in the field of intelligent data analysis

2. Understand the main architectures of deep neural networks, namely convolutional networks,
recurrent networks and transformers.

3. Develop deep neural networks for application to practical problems

4. Understand the main characteristics of reinforcement learning and understand the situations in which it
should be applied

5. Use machine learning tools for the development, training and validation of data analysis models

1. Deep Neural Networks

2. Convolutional networks for computer vision

3. Recurrent networks

4. Natural language processing

5. Transformers

6. Reinforcement learning

7. Generative models

8. Application of TensorFlow, Keras and Hugging Face in the development of deep neural networks

There are 4 assessment components:

A. Short theoretical quizzes (12.5%): 4 small individual multiple-choice quizzes given at the end of theoretical lectures.

B. Short laboratory quizzes (12.5%): 2 small challenges designed to complement/expand on problems covered in lab classes. The work is carried out in groups of 2 students. Submission must be completed by the beginning of the following class.

C. Seminar (25%): Study of a topic in the field of deep learning. These topics are directly related to the course material but will not be covered during lectures. The goal of this assignment is for students to research, learn, and understand the topic assigned to them. As part of the work, students must produce a brief document presenting the topic and give an in-class presentation. The work is carried out in groups of 2 students. The seminar may be submitted and presented only once, according to the date specified in the assignment description. The grade obtained is valid for all exam periods, including the special period. This component has no minimum grade requirement and cannot be improved.

D. Written exam: This test covers the theoretical and theoretical-practical components of the course material. The exam requires a minimum score of 35% of the total exam points.

There are 2 possible assessment schemes:

Continuous and Periodic Assessment: Students complete all 4 assessment components. In this case, the exam counts for 50% of the final grade.

Exclusively Periodic Assessment: Students complete only components C and D (seminar and exam). In this case, the exam counts for 75% of the final grade. The exam for this option will include an additional section.

NAO