Artificial Neural Networks and Deep Learning (4577) |
| Language of instruction : English |
| Credits: 4,0 | | | | | Period: quarter 3 (4sp) | | | | | 2nd Chance Exam1: Yes | | | | | Final grade2: Numerical |
| | | Exam contract: not possible |
|
Sequentiality
|
| |
|
No sequentiality
|
|
|
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, ...).
|
|
|
|
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 student implements two small and one large machine learning projects. 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 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. |
|
|
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | A student must take part in all components of the evaluation. The student must submit the homeworks and report by the dates communicated on Blackboard. |
|
|
|
| Consequences | If a student does not take part in all evaluation components or submits a component too late, he/she will receive an 'X' for the course. |
|
|
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
|
|
| Compulsory textbooks (bookshop) |
| |
Textbook 1:
Deep learning with Python, Francois Chollet, Second Edition, Manning Publications Co.,
ISBN: 9781617296864 |
|
|
| Remarks |
| |
Pre-recorded lectures and the accompanying slides will be made available on blackboard. |
|
|
Learning outcomes Master of Statistics and Data Science
|
- 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 can put research and consulting aspects of one or more statistical fields into practice. | - EC
| The student has the habit to assess data quality and integrity. | - 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
| 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 is capable of acquiring new knowledge. | - 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 = learning outcomes DC = partial outcomes BC = evaluation criteria |
| Offered in | Tolerance3 |
|
2nd year Master Bioinformatics
|
J
|
|
2nd year Master Data Science
|
J
|
|
exchange bachelor informatica K
|
J
|
|
exchange master informatica K
|
J
|
|
Exchange Programme Statistics
|
J
|
|
|
1 Education, Examination and Legal Position Regulations art.12.2, section 2. |
| 2 Education, Examination and Legal Position Regulations art.15.1, section 3. |
3 Education, Examination and Legal Position Regulations art.16.9, section 2.
|
|