Mini projects on machine learning and control systems

Code:

MPSAC01

Acronym:

MPSAC

Keywords
Classification	Keyword
CNAEF	Engineering and related techniques

Instance: 2024/2025 - 1S (of 07-10-2024 to 22-11-2024)

Active?	Yes
Responsible unit:	Department of Electrical and Computer Engineering
Course/CS Responsible:	Mini projects on machine learning and control systems

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
L.AERO	0	Syllabus	3	-	1,5	12	40,5
L.BIO	3	Syllabus	3	-	1,5	12	40,5
L.EA	0	Syllabus	2	-	1,5	12	40,5
L.EC	1	Syllabus	2	-	1,5	12	40,5
L.EEC	1	Syllabus	2	-	1,5	12	40,5
L.EGI	0	Syllabus	2	-	1,5	12	40,5
L.EIC	20	Syllabus	2	-	1,5	12	40,5
			3
L.EM	5	Syllabus	3	-	1,5	12	40,5
L.EMAT	0	Syllabus	3	-	1,5	12	40,5
L.EMG	0	Plano de estudos oficial a partir de 2008/09	2	-	1,5	12	40,5
			3
MPSAC	0	Syllabus	1	-	1,5	12	40,5

Teaching language

Portuguese

Objectives

• provide students with basic skills in the design, development and implementation of simple learning and control algorithms. The proposed algorithms make use of data to improve their performance and have applications in several scientific areas of engineering, including, environmental, bioengineering, civil, data sciences, computer and information sciences, electrotechnics, physics, mechanics, nanotechnology and chemistry; which makes this topic transversal.


• prepare students to solve mini-projects in groups, promoting the development of complementary skills (soft skills), namely: teamwork, cooperation, peer communication, time management, resource management, stress management.

Learning outcomes and competences

• Explanation of the basic functioning of simple learning and control algorithms;


• Development of small projects using Python program modules on the Colab notebook platform that includes data processing and attribute extraction, learning and control;


• Development of soft skills in the areas of teamwork, cooperation, peer communication, time management, resource management and stress management.

Working method

Presencial

Program

• Introduction to basic concepts of machine learning systems for detection and classification.


• Introduction to the basic concepts of control systems.


• Basic principles of a complete system of data/signal acquisition, data processing and attribute extraction, learning and control.


• Development and testing of learning and control mini-projects using simple modules programmed in python on the Colab notebook platform.

Mandatory literature

Åström, K. J., & Murray, R. M.; Feedback systems., Princeton university press.
Müller, A. C., & Guido, S.; Introduction to machine learning with Python: a guide for data scientists.

Teaching methods and learning activities

The teaching-learning methodology is based on the non-requirement of any pre-knowledge or previous competence on the part of students in programming languages and algorithms, and is therefore suitable for any undergraduate or master's student.


According to the program, classes include theoretical and laboratory typologies. The theoretical part consists of lectures to expose machine learning subjects and control systems, accompanied by examples and demonstrations. The practical-laboratory part is focused on application work, namely the development of learning and control mini-projects. At this stage, students will be able to apply and test the knowledge acquired

Evaluation Type

Distributed evaluation without final exam

Assessment Components

Designation	Weight (%)
Trabalho escrito	15,00
Trabalho laboratorial	85,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Estudo autónomo	28,50
Frequência das aulas	12,00
Total:	40,50

Eligibility for exams

Active participation in the proposed activities

Calculation formula of final grade

• Two components will be considered:

• EIW - Exercises proposed as Individual Work in the form of a mini-test

• TL - Laboratory Work

• Final classification calculation formula = 15% EIW + 85% TL