| Language of instruction : English |
| | | Exam contract: not possible |
|
Sequentiality
|
| |
|
No sequentiality
|
There is no data for this choice.
Change the language, year or choose another item in the dropdown list if it is available.
| Degree programme | | Study hours | Credits | P2 SBU | P2 SP | 2nd Chance Exam1 | Tolerance2 | Final grade3 | |
 | 2nd year Master Data Science | Compulsory | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical |  |
|
| | | Learning outcomes |
- EC
| The student can handle scientific quantitative research questions, independently, effectively, creatively, and correctly using state-of-the-art design and analysis methodology and software. | | | - DC
| ... correctly using state-of-the-art analysis methodology. | | | - DC
| ... correctly using state-of-the-art software. | - EC
| The student is capable of acquiring new knowledge. | - EC
| The student has the habit to assess data quality and integrity. | - EC
| The student knows the societal relevance of statistics and data science. | | | - DC
| The student can reflect on and explain the societal relevance of a task, particularly within the programme specialization | - EC
| The student is an effective written and oral communicator, both within their own field as well as across disciplines. | | | - DC
| The student is an effective writer in their own field. | - EC
| The student can put research and consulting aspects of one or more statistical fields into practice. | - EC
| The student is able to correctly use the theory, either methodologically or in an application context or both, thus contributing to scientific research within the field of statistical science, data science, or within the field of application. | | | - DC
| The student is able to correctly use the theory in an application context, thus contributing to scientific research within the field of application. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
|
This course gives an introduction to neural networks and deep learning. The emphasis lies on acquiring a conceptual understanding of the current state of the art, and implementing these methods with the Tensorflow and Keras software libraries.
The book 'Deep learning with Python, Second Edition' from Francois Chollet is followed.
The student implements two small and one large machine learning projects in Google Colab.
The following things are covered:
- History of machine learning and deep learning.
- Mathematical concepts of neural networks.
- Fundamental concepts in machine learning: choice of loss function, feature engineering, overfitting, ...
- Best practices for practical implementations: hyperparameter optimization, model ensembling, ...
- Convolutional neural networks. Applied to image data, both for classification and segmentation.
- Recurrent neural networks such as LSTM and GRU. Applied to time series data.
- The Keras and Tensorflow software libraries, including more advanced techniques such as the functional API, callbacks, and Tensorboard.
|
|
|
Period 2 Credits 4,00
| 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 needs to pass this component of the evaluation. |
|
|
|
|
|
|
|
|
|
| Other evaluation method during teaching period | 40 % |
|
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student needs to pass this component of the evaluation. |
|
|
|
|
|
|
|
| Written exam | 40 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student needs to pass this component of the evaluation. |
|
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | A student must at least attend all components of the evaluation.
A student must obtain a tolerable exam result (≥8/20) for each component to be able to pass the programme component.
The student must submit the homeworks and project by the dates communicated on Blackboard. |
|
|
|
| Consequences | If a student does not attend one of the evaluation components, he/she will receive an 'A - unauthorized absence' for the programme component.
If the student achieves less than 8/20 in part of this programme component, this lowest partial grade will be the final grade for the entire programme component for the examination opportunity concerned.
If the homeworks and projects are not submitted or are submitted late, the student will receive 0 for the homework or project.
For the following partial evaluations, the ability to complete a particular assignment within a given timeframe is part of the evaluation: the two homeworks and the project. Students in special circumstances who have been granted extra time as a special arrangement can therefore not invoke such arrangements for the above partial evaluations. |
|
|
|
| Additional information | The exam counts for a total of 8 points.
Points for the first homework (1.5 points), second homework (2.5 points), and project (8 points) are awarded during the teaching period. |
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
|
|
| Prerequisites |
| |
- The student has a basic proficiency in Python, or medium to advanced proficiency in another programming language.
- The student has a basic understanding of vector algebra (dot product, transpose, ...) and calculus (gradient, chain rule for derivatives, ...).
|
|
|
| Compulsory textbooks (bookshop) |
| |
[Deep learning with Python],[Francois Chollet],[Second Edition],[Manning Publications Co.],[9781617296864],[To be published in the fall of 2021. Already available online.] |
|
|
| Remarks |
| |
Pre-recorded lectures and the accompanying slides will be made available on blackboard. |
|
|
|
|
|
| 2nd year Master Bioinformatics | Optional | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
| Exchange Programme Statistics | Optional | 108 | 4,0 | 108 | 4,0 | Yes | Yes | Numerical | |
|
| | | Learning outcomes |
- EC
| The student can handle scientific quantitative research questions, independently, effectively, creatively, and correctly using state-of-the-art design and analysis methodology and software. | | | - DC
| ... correctly using state-of-the-art analysis methodology. | | | - DC
| ... correctly using state-of-the-art software. | - EC
| The student is capable of acquiring new knowledge. | - EC
| The student has the habit to assess data quality and integrity. | - EC
| The student knows the societal relevance of statistics and data science. | | | - DC
| The student can reflect on and explain the societal relevance of a task, particularly within the programme specialization | - EC
| The student is an effective written and oral communicator, both within their own field as well as across disciplines. | | | - DC
| The student is an effective writer in their own field. | - EC
| The student can put research and consulting aspects of one or more statistical fields into practice. | - EC
| The student is able to correctly use the theory, either methodologically or in an application context or both, thus contributing to scientific research within the field of statistical science, data science, or within the field of application. | | | - DC
| The student is able to correctly use the theory in an application context, thus contributing to scientific research within the field of application. |
|
| | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
|
|
This course gives an introduction to neural networks and deep learning. The emphasis lies on acquiring a conceptual understanding of the current state of the art, and implementing these methods with the Tensorflow and Keras software libraries.
The book 'Deep learning with Python, Second Edition' from Francois Chollet is followed.
The student implements two small and one large machine learning projects in Google Colab.
The following things are covered:
- History of machine learning and deep learning.
- Mathematical concepts of neural networks.
- Fundamental concepts in machine learning: choice of loss function, feature engineering, overfitting, ...
- Best practices for practical implementations: hyperparameter optimization, model ensembling, ...
- Convolutional neural networks. Applied to image data, both for classification and segmentation.
- Recurrent neural networks such as LSTM and GRU. Applied to time series data.
- The Keras and Tensorflow software libraries, including more advanced techniques such as the functional API, callbacks, and Tensorboard.
|
|
|
Period 2 Credits 4,00
| 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 needs to pass this component of the evaluation. |
|
|
|
|
|
|
|
|
|
| Other evaluation method during teaching period | 40 % |
|
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student needs to pass this component of the evaluation. |
|
|
|
|
|
|
|
| Written exam | 40 % |
|
| Transfer of partial marks within the academic year | ✔ |
|
| Conditions transfer of partial marks within the academic year | The student needs to pass this component of the evaluation. |
|
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | A student must at least attend all components of the evaluation.
A student must obtain a tolerable exam result (≥8/20) for each component to be able to pass the programme component.
The student must submit the homeworks and project by the dates communicated on Blackboard. |
|
|
|
| Consequences | If a student does not attend one of the evaluation components, he/she will receive an 'A - unauthorized absence' for the programme component.
If the student achieves less than 8/20 in part of this programme component, this lowest partial grade will be the final grade for the entire programme component for the examination opportunity concerned.
If the homeworks and projects are not submitted or are submitted late, the student will receive 0 for the homework or project.
For the following partial evaluations, the ability to complete a particular assignment within a given timeframe is part of the evaluation: the two homeworks and the project. Students in special circumstances who have been granted extra time as a special arrangement can therefore not invoke such arrangements for the above partial evaluations. |
|
|
|
| Additional information | The exam counts for a total of 8 points.
Points for the first homework (1.5 points), second homework (2.5 points), and project (8 points) are awarded during the teaching period. |
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
|
|
| Prerequisites |
| |
- The student has a basic proficiency in Python, or medium to advanced proficiency in another programming language.
- The student has a basic understanding of vector algebra (dot product, transpose, ...) and calculus (gradient, chain rule for derivatives, ...).
|
|
|
| Compulsory textbooks (bookshop) |
| |
[Deep learning with Python],[Francois Chollet],[Second Edition],[Manning Publications Co.],[9781617296864],[To be published in the fall of 2021. Already available online.] |
|
|
| Remarks |
| |
Pre-recorded lectures and the accompanying slides will be made available on blackboard. |
|
|
|
|
|
1 examination regulations art.1.3, section 4. |
| 2 examination regulations art.4.7, section 2. |
3 examination regulations art.2.2, section 3.
|
| Legend |
| SBU : course load | SP : ECTS | N : Dutch | E : English |
|