Reconhecimento de padrões e aprendizado de máquina

2023/02

General Information

Objective: Study of the main deep learning methods and their applications.

Syllabus: Machine learning basics; Deep Feedforward Networks; Convolutional Neural Networks (CNN), Recurrent Neural Networks; Segmentation and Object Recognition; Frameworks for deep learning and Practical Aspects; Applications of deep learning models for real-world problems.

Duration: 60 hours (19 weeks).

Time: Tuesdays (17:50 - 21:10) - synchronous (SYN) and asynchronous (ASYN) classes.

Grade: Assignments (50%) and Final Project (50%).

Lecturer: André Eugenio Lazzaretti and Heitor Silvério Lopes.

Collaborators (PhD students): Andrei Inácio, Matheus Gutoski, Anderson Brilhador.

Bibliography and Support Materials

Books

Other Courses: 

Week 1 - 16/08

Content

DERLEI, LUIGI, MATEO, LEONARDO, ANGELO, LEONARDO AUGUSTINHO

Week 1 (15/08): Predicting Continuous Target Variables with Regression Analysis (ASYN)


Week 2, 3, and 4 (22/08, 29/08 and 05/09): Assignment - Regression (ASYN)


Week 5 (12/09): Working with Unlabeled Data – Clustering Analysis (ASYN)


Week 6 (19/09): Assignment - Clustering (ASYN)


Week 7 (26/09) - EVENTO DAELN 


Week 8 (03/10) - Assignment - Clustering cont. (ASYN)

ANTONIO, ITALO, VICTOR HUGO, EDUARDO, GUILHERME, MARIO, MATHEUS, MELISSA

Preliminary content (watch the content you need to reinforce your knowledge):


Week 1 (15/08) - Training Simple Machine Learning Algorithms (ASYN)


Week 2 (22/08) - A Tour of Machine Learning Classifiers Using scikit-learn (ASYN)


Week 3 (29/08) - Building Good Training Sets - Data Preprocessing (ASYN)


Week 4 (05/09) - Compressing Data via Dimensionality Reduction (ASYN)


Week 5 (12/09) - Python and Machine Learning Basics (ASYN)


Week 6 (19/09) - Learning Best Practices for Model Evaluation and Hyperparameter Tuning (ASYN)


Week 7 (26/09) - EVENTO DAELN


Week 8 (03/10) - Classification with scikit-learn (ASYN)

Week 9 to 19 - 10/10 to 19/12 - in sync with Deep Learning Course - CPGEI

Check here.