School / Prep
ENSEIRB-MATMECA
Internal code
ET9IA347
Description
This module proposes to study recent systems in deep learning. On the one hand, we'll be looking at recurrent systems, and on the other at non-supervised generative approaches such as antigonistic network methods.
Teaching hours
- CMLectures9h
- TIIndividual work12h
- PRACTICAL WORKPractical work12h
Syllabus
Recurrent approaches (RNN, LSTM, etc.)
Knowledge transfer approaches
Antagonistic network generative methods (GAN, generator, discriminator, etc.)
Image classification
Object recognition
Super-resolution
Translation in image processing (colorization, style transfer, etc.)
Further information
Signal and image processing
Assessment of knowledge
Initial assessment / Main session - Tests
Type of assessment | Type of test | Duration (in minutes) | Number of tests | Test coefficient | Eliminatory mark in the test | Remarks |
---|---|---|---|---|---|---|
Final inspection | Written | 60 | 1 | without document calculator allowed |
Second chance / Catch-up session - Tests
Type of assessment | Type of test | Duration (in minutes) | Number of tests | Test coefficient | Eliminatory mark in the test | Remarks |
---|---|---|---|---|---|---|
Final test | Written | 60 | 1 | without document calculator allowed |