| Language of instruction : English |
|
Sequentiality
|
| |
|
Advising sequentiality bound on the level of programme components
|
| |
|
Advice
It is advised to have taken up the following course in the study programme to date: '4674 Fundamenten van materiaalmodellering'.
It is advised that this course is taken in tandem with the specialisation course '4907 Big data and high throughput based modeling for energy materials'.
|
|
|
|
| Degree programme | | Study hours | Credits | P1 SBU | P1 SP | 2nd Chance Exam1 | Tolerance2 | Final grade3 | |
 | 2nd year Master of Materiomics traject opleidingsonderdelen | Optional | 81 | 3,0 | 81 | 3,0 | Yes | Yes | Numerical |  |
|
| | | Learning outcomes |
- EC
| EC 2. The graduate of the Master of Materiomics programme can combine chemical and physical principles enabling the discovery of new material concepts based on an interdisciplinary approach. | | | - DC
| DC2.9 The student is able to assess which concepts, models and methods from different perspectives are most useful in a specific context. The student uses this assessment in selecting the best perspectives. [learning pathway interdisciplinarity - reflection: the student considers different perspectives and is able to reflect critically on them] | - EC
| EC 3. The graduate of the Master of Materiomics programme has insight in how modelling or synthesis methods predict and affect functional properties and is able to design sustainable materials based on in-operando functionality making optimal use of the synergy between computational and experimental methods. | | | - DC
| DC3.1 The student is able to apply techniques for characterization and modeling. | | | - DC
| DC3.2 The student is able to predict properties from structure using modeling methods. | | | - DC
| DC3.4 The student is able to select, justify and optimize the appropriate characterization/modeling technique and method to investigate structure, synthesis, properties of materials and devices. | | | - DC
| DC3.8 The student has knowledge of computational concepts and methods. [learning pathway interdisciplinarity - identification: the student knows which phenomena are studied in the various disciplines and which methods and theories are used] | | | - DC
| DC3.10 The student has knowledge of the added value and shortcomings of experimental and computational approaches and uses their complementarity to leverage the reinforcing effect in the combination of both adapted to the problem/issue at hand. [learning pathway interdisciplinarity - reflection: the student considers different perspectives and is able to reflect critically on them] | - EC
| EC 4. The graduate of the Master of Materiomics programme is able to autonomously consult, summarise and critically interpret international scientific literature, reference it correctly and use it to explore and identify new domains relevant to the field. | | | - DC
| DC4.2 The student is able to correctly and completely reference to scientific literature. | | | - DC
| DC4.3 The student is able to critically interpret, evaluate, compare, and/or summarize relevant scientific literature related to materials-related problems or research questions. | - EC
| EC 5. The graduate of the Master of Materiomics programme can independently design and carry out scientific research: formulate a research question and hypothesis, select the appropriate methods and techniques, critically analyse and interpret the results, formulate conclusions, report scientifically and manage research data. | | | - DC
| DC5.4 The student knows and understands the methods required to process, analyze, and interpret data. | | | - DC
| DC5.10 The student is able to apply various scientific reporting methods e.g., project reporting, article, poster/oral presentation,.... | - EC
| EC 10. The graduate of the Master of Materiomics programme is able to autonomously acquire new knowledge and monitor, evaluate and adjust one’s learning process. | | | - DC
| DC10.3 The student is able to autonomously acquire, process, and critically interpret new information. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
|
The student should have prior knowledge of the following general topics in physics/chemistry:
- basic concepts from quantum mechanics/chemistry
- basic concepts from Newtonian mechanics
- the concepts of chemical bonding and crystal structure
- basic knowledge of the electronic structure of molecules and solids
- basic concepts of statistics
- basic concepts of machine learning ('4674 Fundamenten van materiaalmodellering', 1Ma)
- basic knowledge of programming in python ('4674 Fundamenten van materiaalmodellering', 1Ma)
|
|
|
|
In this course, students gain further competence in the use of Artificial Intelligence within the context of modern materials research. This builds on the knowledge from the course '4674 Fundamenten van materiaalmodellering' (1Ma). The student comes into contact with new advanced methods and delves deeper into the underlying theory. In addition, the use of AI within materials research is made explicit using examples from recent research. Here the link is made to the other courses within the programme. During the project, the student develops a practical case study in machine learning within the specialisation followed by the student.
Within this course, the topics are divided into three themes.
Themes:
1) Deeper introduction to selected AI methods, including ensemble methods, gaussian processes, (deep) neural networks and derived models. In addition, data preparation and cleaning is also introduced.
2) AI within the theoretical/computational context, covering topics such as the representation of molecules and materials in AI, the prediction of simulated physical and chemical properties, and also ML-based atomic potentials.
3) AI within the experimental context, covering topics such as the prediction of measured physical and chemical properties, active learning and closed loop materials design, and topics of interest (e.g. the use of LLM in all aspects of materials research).
The aim of this course is to provide the student with a broad knowledge base and practical skill regarding the various methods and concepts of AI in materials research. Learnings goals are:
- The student can translate physical and chemical concepts from and into computational concepts with special attention to the needs of data selection and cleaning
- The student has a broad general knowledge of the underlying theories for advanced AI methods
- The student has knowledge of different methods, their interrelation and advantages and disadvantages
- Given a practical problem, the student can develop a practical workflow, select relevant methods, and analyse and report the results
- The student can communicate performed AI modelling and material design in writing and orally
- The student can independently review recent literature, critically interpret and apply it to relevant material design issues
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Response lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
Video lectures with quiz ✔
|
|
|
|
|
|
|
|
Case study ✔
|
|
|
|
Paper ✔
|
|
|
|
Presentation ✔
|
|
|
|
Workshop ✔
|
|
|
|
Period 1 Credits 3,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 20 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student achieves a minimum of 10/20. |
|
|
|
|
|
|
|
|
| Written exam | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student achieves a minimum of 10/20. |
|
|
|
|
|
|
|
|
| Oral exam | 20 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student achieves a minimum of 10/20. |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | The (draft & final) paper should be submitted. |
|
|
|
| Consequences | The student who did not submit the paper for an unjustified reason will receive a result of "N = evaluation not completed in full: unjustifiably absent for subsection(s) of the evaluation" for the course unit. |
|
|
|
| Additional information | For students with an exam contract, permanent evaluation items during the teaching period (e.g., paper, reports, presentation) are replaced by an alternative, individual assignment. |
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The written closed-book examination during the examination period may be retaken. Permanent evaluation items during the teaching period (e.g., paper, reports, presentation) are replaced by an alternative, individual assignment. |
|
|
|
|
|
| Compulsory textbooks (bookshop) |
| |
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems,Aurélien Géron,3,O'Reilly,9781098125974,(1st edition is very different, so not to be used) |
|
|
| Compulsory course material |
| |
Course notes, powerpoint slides, selected (review) articles: Blackboard
Obligatory software on personal hardware:
* Python IDE and packaging system (e.g. Anaconda)
* Python packages: Jupyter notebooks, scikit learn, tensorflow, RDkit, and standard numerical and scientific packages (including dependencies).
All these are free to install. |
|
|
|
|
|
| Exchange Programme materiomics | Optional | 81 | 3,0 | 81 | 3,0 | Yes | Yes | Numerical | |
|
| |
|
|
The student should have prior knowledge of the following general topics in physics/chemistry:
- basic concepts from quantum mechanics/chemistry
- basic concepts from Newtonian mechanics
- the concepts of chemical bonding and crystal structure
- basic knowledge of the electronic structure of molecules and solids
- basic concepts of statistics
- basic concepts of machine learning ('4674 Fundamenten van materiaalmodellering', 1Ma)
- basic knowledge of programming in python ('4674 Fundamenten van materiaalmodellering', 1Ma)
|
|
|
|
In this course, students gain further competence in the use of Artificial Intelligence within the context of modern materials research. This builds on the knowledge from the course '4674 Fundamenten van materiaalmodellering' (1Ma). The student comes into contact with new advanced methods and delves deeper into the underlying theory. In addition, the use of AI within materials research is made explicit using examples from recent research. Here the link is made to the other courses within the programme. During the project, the student develops a practical case study in machine learning within the specialisation followed by the student.
Within this course, the topics are divided into three themes.
Themes:
1) Deeper introduction to selected AI methods, including ensemble methods, gaussian processes, (deep) neural networks and derived models. In addition, data preparation and cleaning is also introduced.
2) AI within the theoretical/computational context, covering topics such as the representation of molecules and materials in AI, the prediction of simulated physical and chemical properties, and also ML-based atomic potentials.
3) AI within the experimental context, covering topics such as the prediction of measured physical and chemical properties, active learning and closed loop materials design, and topics of interest (e.g. the use of LLM in all aspects of materials research).
The aim of this course is to provide the student with a broad knowledge base and practical skill regarding the various methods and concepts of AI in materials research. Learnings goals are:
- The student can translate physical and chemical concepts from and into computational concepts with special attention to the needs of data selection and cleaning
- The student has a broad general knowledge of the underlying theories for advanced AI methods
- The student has knowledge of different methods, their interrelation and advantages and disadvantages
- Given a practical problem, the student can develop a practical workflow, select relevant methods, and analyse and report the results
- The student can communicate performed AI modelling and material design in writing and orally
- The student can independently review recent literature, critically interpret and apply it to relevant material design issues
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Response lecture ✔
|
|
|
|
Small group session ✔
|
|
|
|
Video lectures with quiz ✔
|
|
|
|
|
|
|
|
Case study ✔
|
|
|
|
Paper ✔
|
|
|
|
Presentation ✔
|
|
|
|
Workshop ✔
|
|
|
|
Period 1 Credits 3,00
| Evaluation method | |
|
| Written evaluaton during teaching periode | 20 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student achieves a minimum of 10/20. |
|
|
|
|
|
|
|
|
| Written exam | 60 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student achieves a minimum of 10/20. |
|
|
|
|
|
|
|
|
| Oral exam | 20 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student achieves a minimum of 10/20. |
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | The (draft & final) paper should be submitted. |
|
|
|
| Consequences | The student who did not submit the paper for an unjustified reason will receive a result of "N = evaluation not completed in full: unjustifiably absent for subsection(s) of the evaluation" for the course unit. |
|
|
|
| Additional information | For students with an exam contract, permanent evaluation items during the teaching period (e.g., paper, reports, presentation) are replaced by an alternative, individual assignment. |
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
| Explanation (English) | The written closed-book examination during the examination period may be retaken. Permanent evaluation items during the teaching period (e.g., paper, reports, presentation) are replaced by an alternative, individual assignment. |
|
|
|
|
|
| Compulsory textbooks (bookshop) |
| |
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems,Aurélien Géron,3,O'Reilly,9781098125974,(1st edition is very different, so not to be used) |
|
|
| Compulsory course material |
| |
Course notes, powerpoint slides, selected (review) articles: Blackboard
Obligatory software on personal hardware:
* Python IDE and packaging system (e.g. Anaconda)
* Python packages: Jupyter notebooks, scikit learn, tensorflow, RDkit, and standard numerical and scientific packages (including dependencies).
All these are free to install. |
|
|
|
|
|
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 |
|