| Language of instruction : English |
|
Sequentiality
|
| |
|
No sequentiality
|
| Degree programme | | Study hours | Credits | P1 SBU | P1 SP | 2nd Chance Exam1 | Tolerance2 | Final grade3 | |
 | Master of Electronics and ICT Engineering Technology | Compulsory | 135 | 5,0 | 135 | 5,0 | Yes | Yes | Numerical |  |
|
| | | Learning outcomes |
- EC
| EC1 - The holder of the degree thinks and acts professionally with an appropriate engineering attitude and continuous focus on personal development, adequately communicates, effectively cooperates, takes into account the sustainable, economical, ethical, social and/or international context and is hereby aware of the impact on the environment. | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student interprets the status of a machine learning model, for example high-variance vs high bias, and deduces appropriate actions to further improve the performance of the model. | | | - DC
| DC-M9 - can communicate in oral and in written (also graphical) form. | | | | - BC
| The students makes a report of the findings of a project. This report consists mainly of figures illustrating the performance of the machine learning system. | | | - DC
| DC-M10 - can function constructively and responsibly as member of a (multidisciplinary) team. | | | | - BC
| The students work on a project in teams of two. They need to arrange the work among themselves. | | | - DC
| DC-M12 - shows a suitable engineering attitude. | | | | - BC
| A critical reflection of the project results is asked and the next step the students would tackle. | - EC
| EC3 - The holder of the degree has advanced knowledge of and insight in principles and applications of automation and sensor technology and signal processing and can independently recognise, critically analyse and create methodical solutions for complex, practical design or optimisation problems with eye for data processing and implementation, with attention to topical technological developments. | | | - DC
| DC-M1 - has knowledge of the basic concepts, structures and coherence. | | | | - BC
| Basic machine learning concepts need to be known.
*supervised techniques: classification, regression
*non-supervised techniques, clustering, datareduction
*Recomendersystems | | | - DC
| DC-M2 - has insight in the basic concepts and methods. | | | | - BC
| The student has insights in following techniques:
regression; logistic regression; neural networks; support vector machines; collaborative filtering of recommendersystems; naive Bayesian techniques. | | | - DC
| DC-M3 - can recognize problems, plan activities and perform accordingly. | | | | - BC
| The student can reflect on the selection of the appropriate method in Machine Learning. | | | - DC
| DC-M4 - can gather, measure or obtain information and refer to it correctly. | | | | - BC
| The student is able to look up certain machine learning algorithms in literature or online sources. | | | - DC
| DC-M5 - can analyze problems, logically structure and interpret them. | | | | - BC
| The student can analyse the quality and characteristics of the data. | | | - DC
| DC-M6 - can select methods and make calculated choices to solve problems or design solutions. | | | | - BC
| The student is able to select the relevant algorithms and tools to perform the given tasks. | | | | - BC
| The student is able to set up an machine learning pipeline based on fuzzy specifications. | | | - DC
| DC-M7 - can use selected methods and tools to implement solutions and designs. | | | | - BC
| The student can build a machine learning pipeline based on the specifications | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student can evaluate the performance of the machine learning model and can suggest adjustments to improve its performance. | - EC
| EC7 - The holder of the degree has specialist knowledge of and insight in principles and applications within the domains of computer technology and algorithms of programming languages, in which he/she can initiate, plan, critically analyse and create solid solutions with eye for data processing and implementation, with the help of simulation techniques or advanced tools, while being aware of potential mistakes, practical constraints and with attention to the topical technological developments. | | | - DC
| DC-M1 - has knowledge of the basic concepts, structures and coherence. | | | | - BC
| See in EC3. | | | - DC
| DC-M2 - has insight in the basic concepts and methods. | | | | - BC
| See in EC3. | | | - DC
| DC-M3 - can recognize problems, plan activities and perform accordingly. | | | | - BC
| See in EC3. | | | - DC
| DC-M4 - can gather, measure or obtain information and refer to it correctly. | | | | - BC
| See in EC3. | | | - DC
| DC-M5 - can analyze problems, logically structure and interpret them. | | | | - BC
| See in EC3. | | | - DC
| DC-M6 - can select methods and make calculated choices to solve problems or design solutions. | | | | - BC
| See in EC3. | | | - DC
| DC-M7 - can use selected methods and tools to implement solutions and designs. | | | | - BC
| See in EC3. | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| See in EC3. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 5,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Master of Electromechanical Engineering Technology optie automation | Compulsory | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| | | Learning outcomes |
- EC
| EC1 - The holder of the degree thinks and acts professionally with an appropriate engineering attitude and continuous focus on personal development, adequately communicates, effectively cooperates, takes into account the sustainable, economical, ethical, social and/or international context and is hereby aware of the impact on the environment. | | | - DC
| DC-M8 - The student can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student interprets the status of a machine learning model, for example high-variance vs high bias, and deduces appropriate actions to further improve the performance of the model. | | | - DC
| DC-M9 - The student can communicate in oral and in written (also graphical) form. | | | | - BC
| The students makes a report of the findings of a project. This report consists mainly of figures illustrating the performance of the machine learning system. | | | - DC
| DC-M10 - The student can function constructively and responsibly as member of a (multidisciplinary) team. | | | | - BC
| The students work on a project in teams of two. They need to arrange the work among themselves. | | | - DC
| DC-M12 - The student shows a suitable engineering attitude. | | | | - BC
| A critical reflection of the project results is asked and the next step the students would tackle. | - EC
| EC5 - The holder of the degree has specialist knowledge of and insight in principles and applications within the domains of material science, production and mechanical design or the domain of automation in which he/she can independently identify and critically analyse unfamiliar, complex design or optimisation problems, and methodologically create solutions with eye for data processing and implementation, with the help of numerical simulation techniques or advanced tools, aware of potential mistakes, practical constraints and with attention to the recent technological developments. | | | - DC
| DC-M1 - The student has knowledge of the basic concepts, structures and coherence. | | | | - BC
| Basic machine learning concepts need to be known. *supervised techniques: classification, regression *non-supervised techniques, clustering, datareduction *Recomendersystems | | | - DC
| DC-M2 - The student has insight in the basic concepts and methods. | | | | - BC
| The student has insights in following techniques: regression; logistic regression; neural networks; support vector machines; collaborative filtering of recommendersystems; naive Bayesian techniques. | | | - DC
| DC-M3 - The student can recognize problems, plan activities and perform accordingly. | | | | - BC
| The student can reflect on the selection of the appropriate method in Machine Learning. | | | - DC
| DC-M4 - The student can gather, measure or obtain information and refer to it correctly. | | | | - BC
| The student is able to look up certain machine learning algorithms in literature or online sources. | | | - DC
| DC-M5 - The student can analyze problems, logically structure and interpret them. | | | | - BC
| The student can analyse the quality and characteristics of the data. | | | - DC
| DC-M6 - The student can select methods and make calculated choices to solve problems or design solutions. | | | | - BC
| The student is able to select the relevant algorithms and tools to perform the given tasks. | | | | - BC
| The student is able to set up an machine learning pipeline based on fuzzy specifications. | | | - DC
| DC-M7 - The student can use selected methods and tools to implement solutions and designs. | | | | - BC
| The student can build a machine learning pipeline based on the specifications. | | | - DC
| DC-M8 - The student can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student can evaluate the performance of the machine learning model and can suggest adjustments to improve its performance. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 4,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| 3rd year Bachelor of Engineering Technology - Electronics and ICT Engineering Technology | Compulsory | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
| 3rd year Bachelor of Engineering Technology - Software Systems Engineering Technology | Compulsory | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| | | Learning outcomes |
- EC
| EC1 - The holder of the degree possesses general scientific and technological application-oriented knowledge of the basic concepts, structures and coherence of the specific domain. | | | - DC
| EA-INF 1.3 The student knows the concepts and methods of machine learning. | | | | - BC
| Basic machine learning concepts need to be known. *supervised techniques: classification, regression *non-supervised techniques, clustering, datareduction *Recomendersystems | - EC
| EC2 - The holder of the degree possesses general scientific and discipline-related engineering-technical insight in the basic concepts, methods, conceptual frameworks and interdependent relations of the specific domain. | | | - DC
| EA-INF 2.3 The student has insights in the concepts and methods of machine learning. | | | | - BC
| The student has insights into the following techniques: regression, logistic regression, neural networks, support vector machines, collaborative filtering of recommender systems, and naive Bayesian methods. | - EC
| EC3 - The holder of the degree is able to recognize problems independently and can take initiative to plan activities and perform accordingly. | | | - DC
| 3.2 The student can plan a technical-scientific project in a structured manner. | | | | - BC
| The student can reflect on the selection of the appropriate method in Machine Learning. | - EC
| EC4 - The holder of the degree can gather and obtain relevant scientific and/or technical information and/or he/she can measure the necessary information efficiently and conscientiously. Additionally, he/she can make correct references to information. | | | - DC
| 4.1 The student can look up scientific and/or technical information in a goal-oriented manner. | | | | - BC
| The student is able to look up certain machine learning algorithms in literature or online sources. | - EC
| EC5 - The holder of the degree can analyse unknown, domain-specific problems, subdivide them, structure them logically, determine the preconditions and interpret the data scientifically. | | | - DC
| EA-INF 5.2 The student can analyse the data of the machine learning problem | | | | - BC
| The student can analyse the quality and characteristis of the data. | - EC
| EC6 - The holder of the degree can select and use adequate solution methods to solve unknown, domain-specific problems and can work methodologically and make solid design choices. | | | - DC
| 6.7 The student is able to make a modular and maintainable design of software. | | | | - BC
| The student is able to set up an machine learning pipeline based on fuzzy specifications. | | | - DC
| EA-INF 6.4 The student is able to select and design a machine learning model | | | | - BC
| The student is able to select the relevant algorithms and tools to perform the given tasks. | - EC
| EC7 - The holder of the degree can use the selected methods and tools innovatively to systematically implement domain-specific solutions and designs while being aware of practical and economic conditions and company-related implications. | | | - DC
| EA-INF 7.3 The student can implement a machine learning model | | | | - BC
| The student can build a machine learning pipeline based on the specifications. | - EC
| EC8 - The holder of the degree can interpret (incomplete) results, can deal with uncertainties and constraints and can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | - DC
| 8.2 The student can reflect critically on a technical-scientific project. | | | | - BC
| The student can evaluate the performance of the machine learning model and can suggest adjustments to improve its performance. | | | | - BC
| The student interprets the status of a machine learning model, for example high-variance vs high bias, and deduces appropriate actions to further improve the performance of the model. | - EC
| EC9 - The holder of the degree can communicate with colleagues in oral and in written form (including in a graphical way) about domain-specific aspects in suited language making use of apt terminology. | | | - DC
| 9.1 The student is able to communicate in writing in a correct, structured and appropriate manner in languages relevant to their field of study.
| | | | - BC
| The students makes a report of the findings of a project. This report consists mainly of figures illustrating the performance of the machine learning system. | - EC
| EC10 - The holder of the degree can function as member of a (multidisciplinary) team using a constructive and responsible approach. | | | - DC
| 10.1 The student has an eye for and contributes to determining the best working method to tackle a shared assignment. | | | | - BC
| The students work on a project in teams of two. They need to arrange the work among themselves. | | | - DC
| 10.2 The student can collaborate actively and constructively with others to achieve a common goal (product). | | | | - BC
| The students work on a project in teams of two. They need to arrange the work among themselves. | - EC
| EC12 - The holder of the degree can act application-oriented and goal-driven and can act academically and professionally with the necessary perseverance and with eye for realism and efficiency, showing a research-oriented attitude towards lifelong learning. | | | - DC
| 12.3 The student adopts an appropriate engineering attitude (accurate, efficient, safe, result-oriented,...). | | | | - BC
| A critical reflection of the project results is asked and the next step the students would tackle. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 4,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Master of Software Systems Engineering Technology | Compulsory | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| | | Learning outcomes |
- EC
| EC1 – The Master of Software Engineering Technology can communicate adequately, cooperate effectively, and take into account the sustainable, economic, ethical, social and/or international context and (s)he is aware of the impact on the environment in all aspects of his/her professional thought-process and agency. (S)he displays an appropriate engineering attitude, including continuous attention to the development of his/her professional competencies --. [people, data literacy and essential software skills]. | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student interprets the status of a machine learning model, for example high-variance vs high bias, and deduces appropriate actions to further improve the performance of the model. | | | - DC
| DC-M9 - can communicate in oral and in written (also graphical) form. | | | | - BC
| The students makes a report of the findings of a project. This report consists mainly of figures illustrating the performance of the machine learning system. | | | - DC
| DC-M10 - can function constructively and responsibly as member of a (multidisciplinary) team. | | | | - BC
| The students work on a project in teams of two. They need to arrange the work among themselves. | | | - DC
| DC-M12 - shows a suitable engineering attitude. | | | | - BC
| A critical reflection of the project results is asked and the next step the students would tackle. | - EC
| EC3 - The Master of Software Engineering Technology has advanced knowledge and understanding of the principles and applications of software engineering, including software development processes, software architectures and the software life cycle, and can apply them, with an understanding of current technological developments, in complex and practice-oriented problem domains. [software engineering] | | | - DC
| DC-M1 - has knowledge of the basic concepts, structures and coherence. | | | | - BC
| Basic machine learning concepts need to be known. *supervised techniques: classification, regression *non-supervised techniques, clustering, datareduction *Recomendersystems. | | | - DC
| DC-M2 - has insight in the basic concepts and methods. | | | | - BC
| The student has insights in following techniques: regression; logistic regression; neural networks; support vector machines; collaborative filtering of recommendersystems; naive Bayesian techniques. | | | - DC
| DC-M3 - can recognize problems, plan activities and perform accordingly. | | | | - BC
| The student can reflect on the selection of the appropriate method in Machine Learning. | | | - DC
| DC-M4 - can gather, measure or obtain information and refer to it correctly. | | | | - BC
| The student is able to look up certain machine learning algorithms in literature or online sources. | | | - DC
| DC-M5 - can analyze problems, logically structure and interpret them. | | | | - BC
| The student can analyse the quality and characteristis of the data. | | | - DC
| DC-M6 - can select methods and make calculated choices to solve problems or design solutions. | | | | - BC
| The student is able to select the relevant algorithms and tools to perform the given tasks. | | | | - BC
| The student is able to set up an machine learning pipeline based on fuzzy specifications. | | | - DC
| DC-M7 - can use selected methods and tools to implement solutions and designs. | | | | - BC
| The student can build a machine learning pipeline based on the specifications. | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student can evaluate the performance of the machine learning model and can suggest adjustments to improve its performance. | - EC
| EC5 - The Master of Software Engineering Technology masters the necessary sets of specialised knowledge and skills for the design of modular, integrated software systems that, on the basis of data acquisition and data analysis, can make intelligent decisions and that are resilient (secure, robust and scalable), within multidisciplinary projects with an applied research and/or innovation component. [intelligent & resilient systems] | | | - DC
| DC-M1 - has knowledge of the basic concepts, structures and coherence.
| | | | - BC
| See in EC3. | | | - DC
| DC-M2 - has insight in the basic concepts and methods.
| | | | - BC
| See in EC3. | | | - DC
| DC-M3 - can recognize problems, plan activities and perform accordingly. | | | | - BC
| See in EC3. | | | - DC
| DC-M4 - can gather, measure or obtain information and refer to it correctly.
| | | | - BC
| See in EC3. | | | - DC
| DC-M5 - can analyze problems, logically structure and interpret them.
| | | | - BC
| See in EC3. | | | - DC
| DC-M6 - can select methods and make calculated choices to solve problems or design solutions.
| | | | - BC
| See in EC3. | | | - DC
| DC-M7 - can use selected methods and tools to implement solutions and designs.
| | | | - BC
| See in EC3. | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| See in EC3. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 4,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Bridging programme Electronics and ICT Engineering Technology - part 2 | Compulsory | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
| Bridging programme Software Systems Engineering Technology - part 2 | Compulsory | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 4,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Master of Energy Engineering Technology (English) | Compulsory | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| | | Learning outcomes |
- EC
| EC1 - The holder of the degree thinks and acts professionally with an appropriate engineering attitude and continuous focus on personal development, adequately communicates, effectively cooperates, takes into account the sustainable, economical, ethical, social and/or international context and is hereby aware of the impact on the environment. | | | - DC
| DC-M8 - The student can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student interprets the status of a machine learning model, for example high-variance vs high bias, and deduces appropriate actions to further improve the performance of the model. | | | - DC
| DC-M9 - The student can communicate in oral and in written (also graphical) form. | | | | - BC
| The students makes a report of the findings of a project. This report consists mainly of figures illustrating the performance of the machine learning system. | | | - DC
| DC-M10 - The student can function constructively and responsibly as member of a (multidisciplinary) team. | | | | - BC
| The students work on a project in teams of two. They need to arrange the work among themselves. | | | - DC
| DC-M12 - The student shows a suitable engineering attitude. | | | | - BC
| A critical reflection of the project results is asked and the next step the students would tackle. | - EC
| EC4 - The holder of the degree has advanced knowledge of and insight in the principles and applications in electrical engineering, possibly complemented with automation or material science and production, in which he/she can independently identify and critically analyse complex, practice-oriented design or optimisation problems, and methodologically create solutions with eye for data processing and implementation and with attention to the recent technological developments. | | | - DC
| DC-M1 - The student has knowledge of the basic concepts, structures and coherence. | | | | - BC
| Basic machine learning concepts need to be known. *supervised techniques: classification, regression *non-supervised techniques, clustering, datareduction *Recomendersystems | | | - DC
| DC-M2 - The student has insight in the basic concepts and methods. | | | | - BC
| The student has insights in following techniques: regression; logistic regression; neural networks; support vector machines; collaborative filtering of recommendersystems; naive Bayesian techniques. | | | - DC
| DC-M3 - The student can recognize problems, plan activities and perform accordingly. | | | | - BC
| The student can reflect on the selection of the appropriate method in Machine Learning. | | | - DC
| DC-M4 - The student can gather, measure or obtain information and refer to it correctly. | | | | - BC
| The student is able to look up certain machine learning algorithms in literature or online sources. | | | - DC
| DC-M5 - The student can analyze problems, logically structure and interpret them. | | | | - BC
| The student can analyse the quality and characteristis of the data. | | | - DC
| DC-M6 - The student can select methods and make calculated choices to solve problems or design solutions. | | | | - BC
| The student is able to select the relevant algorithms and tools to perform the given tasks. | | | | - BC
| The student is able to set up an machine learning pipeline based on fuzzy specifications. | | | - DC
| DC-M7 - The student can use selected methods and tools to implement solutions and designs. | | | | - BC
| The student can build a machine learning pipeline based on the specifications. | | | - DC
| DC-M8 - The student can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student can evaluate the performance of the machine learning model and can suggest adjustments to improve its performance. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 4,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Master of Energy Engineering Technology | Optional | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| | | Learning outcomes |
- EC
| EC1 - The holder of the degree thinks and acts professionally with an appropriate engineering attitude and continuous focus on personal development, adequately communicates, effectively cooperates, takes into account the sustainable, economical, ethical, social and/or international context and is hereby aware of the impact on the environment. | | | - DC
| DC-M8 - The student can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student interprets the status of a machine learning model, for example high-variance vs high bias, and deduces appropriate actions to further improve the performance of the model. | | | - DC
| DC-M9 - The student can communicate in oral and in written (also graphical) form. | | | | - BC
| The students makes a report of the findings of a project. This report consists mainly of figures illustrating the performance of the machine learning system. | | | - DC
| DC-M10 - The student can function constructively and responsibly as member of a (multidisciplinary) team. | | | | - BC
| The students work on a project in teams of two. They need to arrange the work among themselves. | | | - DC
| DC-M12 - The student shows a suitable engineering attitude. | | | | - BC
| A critical reflection of the project results is asked and the next step the students would tackle. | - EC
| EC4 - The holder of the degree has advanced knowledge of and insight in the principles and applications in electrical engineering , possibly complemented with automation or material science and production, in which he/she can independently identify and critically analyse complex, practice-oriented design or optimisation problems, and methodologically create solutions with eye for data processing and implementation and with attention to the recent technological developments. | | | - DC
| DC-M1 - The student has knowledge of the basic concepts, structures and coherence. | | | | - BC
| Basic machine learning concepts need to be known. *supervised techniques: classification, regression *non-supervised techniques, clustering, datareduction *Recomendersystems | | | - DC
| DC-M2 - The student has insight in the basic concepts and methods. | | | | - BC
| The student has insights in following techniques: regression; logistic regression; neural networks; support vector machines; collaborative filtering of recommendersystems; naive Bayesian techniques. | | | - DC
| DC-M3 - The student can recognize problems, plan activities and perform accordingly. | | | | - BC
| The student can reflect on the selection of the appropriate method in Machine Learning. | | | - DC
| DC-M4 - The student can gather, measure or obtain information and refer to it correctly. | | | | - BC
| The student is able to look up certain machine learning algorithms in literature or online sources. | | | - DC
| DC-M5 - The student can analyze problems, logically structure and interpret them. | | | | - BC
| The student can analyse the quality and characteristis of the data. | | | - DC
| DC-M6 - The student can select methods and make calculated choices to solve problems or design solutions. | | | | - BC
| The student is able to set up an machine learning pipeline based on fuzzy specifications. | | | | - BC
| The student is able to select the relevant algorithms and tools to perform the given tasks. | | | - DC
| DC-M7 - The student can use selected methods and tools to implement solutions and designs. | | | | - BC
| The student can build a machine learning pipeline based on the specifications. | | | - DC
| DC-M8 - The student can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student can evaluate the performance of the machine learning model and can suggest adjustments to improve its performance. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 4,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Master of Teaching in Sciences and Technology - Engineering and Technology choice for subject didactics engineering & technology | Optional | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| | | Learning outcomes |
- EC
| 5.2. The master of education is a domain expert ENG & TECH: the EM has a specialised knowledge and understanding of the acquired subject didactics and can creatively conceive, plan and implement them in an educational context and, in particular, as an integrated part of a methodologically and project-based ordered series of actions within a multidisciplinary STEM project with an important research and/or innovation component. | - EC
| 5.3. The master of education is a domain expert ENG & TECH: the EM has advanced or specialised knowledge and understanding of the principles, structure and used technologies of various industrial processes and techniques relevant to the specific subject disciplines and can autonomously recognise, critically analyse and methodically and well-foundedly solve complex, multidisciplinary, non-familiar, practice-oriented design or optimisation problems in these, with an eye for application, selection of materials, automation, safety, environment and sustainability, aware of practical limitations and with attention to current technological developments. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 4,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Exchange Programme Engineering Technology | Optional | 135 | 5,0 | 135 | 5,0 | Yes | Yes | Numerical | |
|
| |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 5,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Exchange Programme Engineering Technology | Optional | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 4,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
| Master of Software Systems Engineering Technology | Transitional curriculum | 135 | 5,0 | 135 | 5,0 | Yes | Yes | Numerical | |
|
| | | Learning outcomes |
- EC
| EC1 – The Master of Software Engineering Technology can communicate adequately, cooperate effectively, and take into account the sustainable, economic, ethical, social and/or international context and (s)he is aware of the impact on the environment in all aspects of his/her professional thought-process and agency. (S)he displays an appropriate engineering attitude, including continuous attention to the development of his/her professional competencies --. [people, data literacy and essential software skills]. | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student interprets the status of a machine learning model, for example high-variance vs high bias, and deduces appropriate actions to further improve the performance of the model. | | | - DC
| DC-M9 - can communicate in oral and in written (also graphical) form. | | | | - BC
| The students makes a report of the findings of a project. This report consists mainly of figures illustrating the performance of the machine learning system. | | | - DC
| DC-M10 - can function constructively and responsibly as member of a (multidisciplinary) team. | | | | - BC
| The students work on a project in teams of two. They need to arrange the work among themselves. | | | - DC
| DC-M12 - shows a suitable engineering attitude. | | | | - BC
| A critical reflection of the project results is asked and the next step the students would tackle. | - EC
| EC3 - The Master of Software Engineering Technology has advanced knowledge and understanding of the principles and applications of software engineering, including software development processes, software architectures and the software life cycle, and can apply them, with an understanding of current technological developments, in complex and practice-oriented problem domains. [software engineering] | | | - DC
| DC-M1 - has knowledge of the basic concepts, structures and coherence. | | | | - BC
| Basic machine learning concepts need to be known. *supervised techniques: classification, regression *non-supervised techniques, clustering, datareduction *Recomendersystems | | | - DC
| DC-M2 - has insight in the basic concepts and methods. | | | | - BC
| The student has insights in following techniques: regression; logistic regression; neural networks; support vector machines; collaborative filtering of recommendersystems; naive Bayesian techniques | | | - DC
| DC-M3 - can recognize problems, plan activities and perform accordingly. | | | | - BC
| The student can reflect on the selection of the appropriate method in Machine Learning. | | | - DC
| DC-M4 - can gather, measure or obtain information and refer to it correctly. | | | | - BC
| The student is able to look up certain machine learning algorithms in literature or online sources. | | | - DC
| DC-M5 - can analyze problems, logically structure and interpret them. | | | | - BC
| The student can analyse the quality and characteristis of the data. | | | - DC
| DC-M6 - can select methods and make calculated choices to solve problems or design solutions. | | | | - BC
| The student is able to select the relevant algorithms and tools to perform the given tasks. | | | | - BC
| The student is able to set up an machine learning pipeline based on fuzzy specifications. | | | - DC
| DC-M7 - can use selected methods and tools to implement solutions and designs. | | | | - BC
| The student can build a machine learning pipeline based on the specifications. | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| The student can evaluate the performance of the machine learning model and can suggest adjustments to improve its performance. | - EC
| EC5 - The Master of Software Engineering Technology masters the necessary sets of specialised knowledge and skills for the design of modular, integrated software systems that, on the basis of data acquisition and data analysis, can make intelligent decisions and that are resilient (secure, robust and scalable), within multidisciplinary projects with an applied research and/or innovation component. [intelligent & resilient systems] | | | - DC
| DC-M1 - has knowledge of the basic concepts, structures and coherence.
| | | | - BC
| See in EC3. | | | - DC
| DC-M2 - has insight in the basic concepts and methods.
| | | | - BC
| See in EC3. | | | - DC
| DC-M3 - can recognize problems, plan activities and perform accordingly. | | | | - BC
| See in EC3. | | | - DC
| DC-M4 - can gather, measure or obtain information and refer to it correctly.
| | | | - BC
| See in EC3. | | | - DC
| DC-M5 - can analyze problems, logically structure and interpret them.
| | | | - BC
| See in EC3. | | | - DC
| DC-M6 - can select methods and make calculated choices to solve problems or design solutions.
| | | | - BC
| See in EC3. | | | - DC
| DC-M7 - can use selected methods and tools to implement solutions and designs.
| | | | - BC
| See in EC3. | | | - DC
| DC-M8 - can evaluate knowledge and skills critically to adjust own reasoning and course of action accordingly. | | | | - BC
| See in EC3. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
- linear regression
- multivariate linear regression
- logistic regression
- neural networks
- bias / variance problems
- k-means clustering
- principle component analysis
- recommender systems
- anomaly detection
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Homework ✔
|
|
|
|
Report ✔
|
|
|
|
Period 1 Credits 5,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | To pass this course, the student must achieve at least 8.0/20 on both parts of the evaluation (the project and the exam). |
|
|
|
| Consequences | If the student achieves less than 8.0/20 on one of the two parts of the evaluation (the project or the exam), the final mark will be the weighted average of both parts with a maximum of 8/20. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The mark of the project is transferred from the first exam period. If the student did not do this project, he can do a new project in the 2nd exam period.
If the student has achieved a mark less than 10/20 on the project, he can apply for a 2nd exam chance. |
|
|
|
|
|
| Recommended course material |
| |
Massive Open Online Course (MOOC) on Coursera: Machine Learning by Andrew Ng. |
|
|
| Remarks |
| |
The Machine Learning course will use the Coursera Machine Learning Course as a modern textbook.
This course is organized in the form of application lectures. The educational method in this course consists of sessions in which the professor introduces new concepts in interactive lectures, accompanied and interleaved with regular practical experiments undertaken by the students. The practical experimental part applies the new concepts in guided assignments. Furthermore, the student will work out, in a groups of 2, a project concerning machine learning applied in healthcare applications. |
|
|
|
|
|
1 Education, Examination and Legal Position Regulations art.12.2, section 2. |
| 2 Education, Examination and Legal Position Regulations art.16.9, section 2. |
3 Education, Examination and Legal Position Regulations art.15.1, section 3.
|
| Legend |
| SBU : course load | SP : ECTS | N : Dutch | E : English |
|