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
Prerequisites Know how to program (preferably in C++) and have notions of probability and statistics.
Mode of delivery Face-to-face
Work placements Not applicable.
Objectives and Learning outcomes of the Course Unit 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.
Course unit contents/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.
Recommended or required reading Main:
-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.
Planned learning activities and teaching methods At the end of this course unit the student should be able to solve problems using neural networks. To accomplish this goal, there are tutorial classes where the student will be able to discuss the concepts, models and language adequate to problem resolution using neural networks, and the project where the student has the opportunity to test her knowledge by writing programs that solve the proposed problems.
Assessment methods and criteria A avaliação é feita com recurso a um relatório de revisão de estado da arte, um projeto prático e a duas apresentações nas aulas relativas ao estado da arte e ao trabalho prático.
O peso de cada componente na nota final é o seguinte:
Relatório estado da arte: 40%
Apresentação e discussão do relatório com estado da arte: 10%
Projeto (relatório + código): 40%
Apresentação e discussão do projeto: 10%

Language Portuguese. Tutorial support is available in English.
Last updated on: 2016-11-05

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