 | Study programme 2019-2020 | Français | |
| Advanced Deep Learning | |||
Learning Activity |
| Code | Lecturer(s) | Associate Lecturer(s) | Subsitute Lecturer(s) et other(s) | Establishment |
|---|---|---|---|---|
| I-INFO-202 |
|
|
| Language of instruction | Language of assessment | HT(*) | HTPE(*) | HTPS(*) | HR(*) | HD(*) | Term |
|---|---|---|---|---|---|---|---|
| Anglais | Anglais | 6 | 6 | 0 | 0 | 0 | Q1 |
| Organisational online arrangements for the end of Q3 2019-2020 assessments (Covid-19) |
|---|
|
| Description of the modifications to the Q3 2019-2020 online assessment procedures (Covid-19) |
| Evaluation methods of Deep Neural Networks Comparative analysis between the different types of deep neural networks (MLP, CNN, RNN, LSTM, Auto-encoders, etc.) |
Content of Learning Activity
- Implemenation and exploitation of new neural architectures (CNN, RNN, LSTM, etc.) ;
- Implementation of the techniques of performance evaluation, interpretation and visualization of deep learning results ;
- Performance optimization: setting hyper parameters, regularization, batch normalization, cross validation, etc.
- Efficient exploitation and portage on embedded hardware
Required Learning Resources/Tools
Not applicable
Recommended Learning Resources/Tools
Not applicable
Other Recommended Reading
Not applicable
Mode of delivery
- Face to face
Type of Teaching Activity/Activities
- Cours magistraux
- Travaux pratiques
- Projet sur ordinateur
- Etudes de cas
Evaluations
The assessment methods of the Learning Activity (AA) are specified in the course description of the corresponding Educational Component (UE)
(*) HT : Hours of theory - HTPE : Hours of in-class exercices - HTPS : hours of practical work - HD : HMiscellaneous time - HR : Hours of remedial classes. - Per. (Period), Y=Year, Q1=1st term et Q2=2nd term