Description

Theory
1

Laboratory
1.5

Instructors

Ana Maria Madureira

Contents

Programme (max. 1000 characters)
CP1. Data Science / Big Data / Data Analytics (2h-30% T + 70% TP)
CP2. Exploratory Data Analysis (15h-30% T + 70% TP)
- Statistical Inference
- Parametric hypothesis tests and Nonparametric hypothesis tests
- Regression and Correlation
CP3. Machine Learning Techniques (31h-20% T + 80% TP).
- Notions and applicability of ML techniques
- Classification of ML Techniques (Supervised learning, Unsupervised learning, Reinforcement learning, Deep learning)
- Optimization and assessment of the models: holdout and K-fold based cross-validation, Evaluation metrics of the regression and classification models
- Supervised Learning Techniques for Regression (Linear Regression Models and Regression Trees)
- Supervised Learning Techniques for Classification (Decision Trees, Neural Networks, kNN, and Support Vector Machines (SVM))
 

Learning Outcomes

It is intended that the student, after completing this UC, recognizes the need to use EDA techniques and understands some of the machine learning (ml algorithms.

Especific Objectives
By the end of this course, the student must be able to:
CO1 Characterize the state of the art of statistical techniques/tools for AED and ML and its potential application in engineering and applied sciences.
CO2-Discuss the basic techniques of EDA and ML for the design of experiences in the field of Data Science.
C03-Analyze and organize data from a variety of sources
CO4-Discuss the different descriptive and inferential statistical techniques to implement EDA
CO5-Identify, select and use appropriate ML tools to support the Data Science process
CO6-Formulate real problems in the context of ML and identify the most appropriate approach to problem solving.
CO7- Construction and optimization of relevant data models
CO8. Evaluate methodical and critically the performance of the models.
CO9-Develop Teamwork and produce technical reports and scientific articles, and oral communication in Portuguese / English.