-
Presentation
Presentation
This course aims to provide students with continuing skills in the field of Artificial Intelligence, equipping them with solid, structured knowledge that will enable them to understand theoretical concepts and develop code to solve practical AI problems.
-
Class from course
Class from course
-
Degree | Semesters | ECTS
Degree | Semesters | ECTS
Bachelor | Semestral | 6
-
Year | Nature | Language
Year | Nature | Language
2 | Mandatory | Português
-
Code
Code
ULHT6634-2129
-
Prerequisites and corequisites
Prerequisites and corequisites
Not applicable
-
Professional Internship
Professional Internship
Não
-
Syllabus
Syllabus
Intermediate notions of AI in various domains. Models: n-Grams, genetic algorithms, linear and logistic regression models, perceptron, neural networks. Activation functions: Linear, Sigmoid, Relu, other approaches. Learning: basic and intermediate notions, action prediction, other approaches.
-
Objectives
Objectives
Know Understand the paradigms and challenges of Artificial Intelligence. Learn fundamental methods and their applications in data-driven knowledge discovery. Data, model selection, model complexity, etc. Understand the advantages and limitations of the Artificial Intelligence methods studied. Do Implement and adapt Artificial Intelligence algorithms. Model real data experimentally Interpret and evaluate experimental results. Validate and compare Artificial Intelligence algorithms. Complementary skills Ability to assess the suitability of methods for data and practical applications. Ability to critically evaluate the results obtained. Autonomy to apply and deepen knowledge in the field of Artificial Intelligence.
-
Teaching methodologies and assessment
Teaching methodologies and assessment
Lecturing consists of theoretical and practical classes. The theoretical component is essentially expository, the theory being presented together with concrete examples. In the practical component, practical programming problems related to the theory taught are developed and solved. In this course unit the evaluation includes the following elements: Theoretical assessment, in the form of written test, exercises, with a weight of 30% in the final grade (minimum grade: 9.5 points). Practical assessment (projects / programming problems / presentations), with a weight of 70% in the final grade (minimum grade: 9.5 points).
-
References
References
T. Mitchell. Machine Learning, McGraw-Hill, 1997. C. M. Bishop. Pattern Recognition and Machine Learning, Springer, 2006.
-
Office Hours
Office Hours
-
Mobility
Mobility
No
