You need to activate javascript for this site.
Menu Conteúdo Rodapé
  1. Home
  2. Courses
  3. Computer Science and Engineering
  4. Neural Networks

Neural Networks

Code 11512
Year 1
Semester S1
ECTS Credits 6
Workload OT(15H)
Scientific area Informatics
Entry requirements Know how to program and have notions of probability and statistics.
Mode of delivery Face-to-face
Work placements Not applicable.
Learning outcomes Introduce the concepts, models and language adequate to problem solving using neural networks.
At the end of this course unit the student should be able to solve problems using neural networks and eventually be able to propose improvements to current methods.
Syllabus 1-Feed-forwd and recurrent networks.
2-Networks for clustering, classification and regression.
3-Reservoir networks.
4-Learning algorithms.
6-Cost functions.
7-Performance evaluation.
8-Shallow versus deep networks.
9-Applications to signal and image processing.
Main Bibliography Main:
-Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press book, 2016
-Neural Networks and Learning Machines (3rd Edition), S. Haykin, Prentice Hall; 3 edition, 2008

-Pattern Recognition and Machine Learning, C. Bishop, Springer, 2006
-Several journals in this area.
Teaching Methodologies and Assessment Criteria The CU works in a tutorial way, so there will be brief presentations of the topics studied to the students, scientific papers will be chosen in the areas of study and the students will studied and present them and an implementation of a chosen method and its presentation will be also done.
The assessment is based on a state-of-the-art review report, a practical project, and two state-of-the-art presentations and practical work.
The weight of each component in the final grade is as follows:
Report state of the art: 40%
Presentation and discussion of the report with state of the art: 10%
Project (report + code): 40%
Presentation and discussion of the project: 10%
Language Portuguese. Tutorial support is available in English.
Last updated on: 2020-01-21

The cookies used in this website do not collect personal information that helps to identify you. By continuing you agree to the cookie policy.