Machine Learning in RoboticsLaajuus (5 cr)
Code: YT00CD08
Credits
5 op
Teaching language
- English
Responsible person
- Tomi Nieminen
Objective
The student understands the significance of machine learning in digitalizing operational environment. The student knows the most common machine learning methods, is able to apply them in practice to existing data and interpret the results of the methods. In particular, the student is able to apply machine learning models in robotics.
Course Competences:
EUR-ACE: Engineering Design, Master's Degree
EUR-ACE: Engineering Practice, Master's Degree
EUR-ACE: Investigations, Master's Degree
Content
- Most common regression and classification models of supervised machine learning and their application in Python programming environment using NumPy, Pandas, Scikit-learn and Tensorflow libraries.
- Linear and logistic regression
- Support Vector Machine
- Neural networks
- Reinforcement learning
Assessment criteria, satisfactory (1)
Sufficient 1: Student has sufficient knowledge of machine learning algorithms and neural networks. Student is able to apply the most common techniques of machine learning and has the sufficient knowledge of the mathematics behind the techniques. Additionally, the student is able to estimate and validate implementation briefly.
Satisfactory 2: Student has satisfactory knowledge of machine learning and neural networks. Student is able to choose a suitable machine learning technique and apply the technical know-how in practice. Student understands the mathematics behind the techniques at a satisfactory level. Additionally, the student is able to estimate and validate implementation superficially.
Assessment criteria, good (3)
Good 3: Student has good knowledge of machine learning algorithms and neural networks. Student is able to choose an appropriate machine learning technique and apply the technical know-how in practice. Student understands well the mathematics behind the techniques at a good level. Additionally, the student is able to estimate and validate implementation well.
Very good 4: Student has very good knowledge of machine learning algorithms and neural networks. Student is able to choose and justify versatilely a machine learning technique and apply the technical know-how in practice. Student understands the mathematics behind the techniques at a very good level. Additionally, the student is able to estimate and validate implementation critically.
Assessment criteria, excellent (5)
Excellent 5: Student has excellent knowledge of machine learning algorithms and neural networks. Student is able to choose and justify machine learning technique and apply the technical know-how in practice. Student understands the mathematics behind the techniques at an excellent level. Additionally, the student is able to estimate and validate implementation critically.
Enrollment
20.11.2024 - 09.01.2025
Timing
07.01.2025 - 30.04.2025
Number of ECTS credits allocated
5 op
Mode of delivery
Face-to-face
Unit
School of Technology
Campus
Main Campus
Teaching languages
- English
Degree programmes
- Master's Degree Programme in Robotics
Teachers
- Tomi Nieminen
Objectives
The student understands the significance of machine learning in digitalizing operational environment. The student knows the most common machine learning methods, is able to apply them in practice to existing data and interpret the results of the methods. In particular, the student is able to apply machine learning models in robotics.
Course Competences:
EUR-ACE: Engineering Design, Master's Degree
EUR-ACE: Engineering Practice, Master's Degree
EUR-ACE: Investigations, Master's Degree
Content
- Most common regression and classification models of supervised machine learning and their application in Python programming environment using NumPy, Pandas, Scikit-learn and Tensorflow libraries.
- Linear and logistic regression
- Support Vector Machine
- Neural networks
- Reinforcement learning
Teaching methods
Virtual study
Evaluation scale
0-5
Evaluation criteria, satisfactory (1-2)
Sufficient 1: Student has sufficient knowledge of machine learning algorithms and neural networks. Student is able to apply the most common techniques of machine learning and has the sufficient knowledge of the mathematics behind the techniques. Additionally, the student is able to estimate and validate implementation briefly.
Satisfactory 2: Student has satisfactory knowledge of machine learning and neural networks. Student is able to choose a suitable machine learning technique and apply the technical know-how in practice. Student understands the mathematics behind the techniques at a satisfactory level. Additionally, the student is able to estimate and validate implementation superficially.
Evaluation criteria, good (3-4)
Good 3: Student has good knowledge of machine learning algorithms and neural networks. Student is able to choose an appropriate machine learning technique and apply the technical know-how in practice. Student understands well the mathematics behind the techniques at a good level. Additionally, the student is able to estimate and validate implementation well.
Very good 4: Student has very good knowledge of machine learning algorithms and neural networks. Student is able to choose and justify versatilely a machine learning technique and apply the technical know-how in practice. Student understands the mathematics behind the techniques at a very good level. Additionally, the student is able to estimate and validate implementation critically.
Evaluation criteria, excellent (5)
Excellent 5: Student has excellent knowledge of machine learning algorithms and neural networks. Student is able to choose and justify machine learning technique and apply the technical know-how in practice. Student understands the mathematics behind the techniques at an excellent level. Additionally, the student is able to estimate and validate implementation critically.