[ 993MLPEDN1U19 ] UE Deep Learning and Neural Nets I
|
|
|
|
 |
| Workload |
Education level |
Study areas |
Responsible person |
Hours per week |
Coordinating university |
| 1,5 ECTS |
M1 - Master's programme 1. year |
(*)Artificial Intelligence |
Günter Klambauer |
1 hpw |
Johannes Kepler University Linz |
|
|
|
| Detailed information |
| Original study plan |
Master's programme Artificial Intelligence 2024W |
| Objectives |
This course will show practical applications and implementations of the contents of the “Deep Learning and Neural Nets I (3 VL)” class. Students will exercise the theory presented in the accompanying lecture and solve programming assignments. Programming assignments will be done in Python using the PyTorch framework.
|
| Subject |
This course teaches how to implement
- a deep learning framework with automatic differentiation
- fully-connected and convolutional layers
- optimisation algorithms and components for accelerating learning in Python and how to build full networks to solve practical tasks.
|
| Criteria for evaluation |
bi-weekly assignments, exam at the end of the semester
|
| Methods |
Slide presentations, presentations on blackboard, discussions, and code examples
|
| Language |
English |
| Changing subject? |
No |
|
|
|
| On-site course |
| Maximum number of participants |
35 |
| Assignment procedure |
Direct assignment |
|
