2024
Artificial Neural Networks
Name: Artificial Neural Networks
Code: INF14382L
6 ECTS
Duration: 15 weeks/156 hours
Scientific Area:
Informatics
Teaching languages: Portuguese
Languages of tutoring support: Portuguese
Sustainable Development Goals
Learning Goals
At the end of the course unit the student should demonstrate:
* Knowledge of neural network approaches and techniques and deep learning with basic and common architectures
* Understanding of the problems and possible approaches associated with the development of solutions based on neural networks
* Knowledge about the design and programming techniques of these architectures and their evaluation
* Knowledge of neural network approaches and techniques and deep learning with basic and common architectures
* Understanding of the problems and possible approaches associated with the development of solutions based on neural networks
* Knowledge about the design and programming techniques of these architectures and their evaluation
Contents
History of neural networks
Introduction: biological neurons, logical computation with neurons
the perceptron
Perceptron Training
Learning Boolean Functions
Limitations of the perceptron
multilayer networks
Network as a universal approximation
Multi-Layer Networks for Regression
Multi-layer networks for Classification
backpropagation algorithm
training procedures
improve convergence
overtraining
Structuring the network
Network size tuning
Explanability of models
Recurring networks and Kohonen networks
Use cases of neural networks
Introduction: biological neurons, logical computation with neurons
the perceptron
Perceptron Training
Learning Boolean Functions
Limitations of the perceptron
multilayer networks
Network as a universal approximation
Multi-Layer Networks for Regression
Multi-layer networks for Classification
backpropagation algorithm
training procedures
improve convergence
overtraining
Structuring the network
Network size tuning
Explanability of models
Recurring networks and Kohonen networks
Use cases of neural networks
Teaching Methods
Teaching methodologies:
* Theoretical classes with introduction of concepts, resolution of exercises and clarification of doubts.
* Practical laboratory classes with proposal of problems that accompany the theoretical material and clarification of doubts during their resolution. Exercises, of gradual difficulty, covering the topics taught, for students to practice the subject.
* Theoretical classes with introduction of concepts, resolution of exercises and clarification of doubts.
* Practical laboratory classes with proposal of problems that accompany the theoretical material and clarification of doubts during their resolution. Exercises, of gradual difficulty, covering the topics taught, for students to practice the subject.
Assessment
Continuous assessment - Consisting of 3 components:
* two written frequencies (30% each)
* development of a project (40%)
Final assessment - Consisting of 2 components:
* written exam (60%)
* project report (40%)
* two written frequencies (30% each)
* development of a project (40%)
Final assessment - Consisting of 2 components:
* written exam (60%)
* project report (40%)
Certificações
