|
Size: 849
Comment:
|
← Revision 13 as of 2022-10-12 11:24:06 ⇥
Size: 1233
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 4: | Line 4: |
| || Date || First meeting: Wednesday 1.6.2022, 14-15, Presentation: Wednesday 13.7, 13- || || Room || First meeting: zoom, Presentation: MAR4.033 || || Trainers || Shinichi Nakajima || || Contact || nakajima@tu-berlin.de || |
|| Date || First meeting: Tuesday 15.11.2022, 14-15, Presentation: Tuesday 24.1.2023 || || Room || First meeting: Via Zoom (find a link at the ISIS page: https://isis.tu-berlin.de/course/view.php?id=31940) , Presentation: MAR4.033 || || Trainers || Shinichi Nakajima, Mattihias Böhm || || Contact || nakajima@tu-berlin.de, matthias.boehm@tu-berlin.de || |
| Line 15: | Line 15: |
* Alignment of Multi-modal Data * Compression in ML Systems * Data Augmentation and Distillation * Data Cleaning for ML * Federated Data Preparation and Learning * Sparsity Exploitation in ML Systems * Model Debugging, Bias, Fairness |
Joint Seminar on Machine Learning and Data Management Systems
Date |
First meeting: Tuesday 15.11.2022, 14-15, Presentation: Tuesday 24.1.2023 |
Room |
First meeting: Via Zoom (find a link at the ISIS page: https://isis.tu-berlin.de/course/view.php?id=31940) , Presentation: MAR4.033 |
Trainers |
Shinichi Nakajima, Mattihias Böhm |
Contact |
|
Credits |
3 ECTS, Elective in the modules "Machine Learning I", "Machine Learning II", and "Cognitive Algorithms" |
This is a joint research-oriented seminar of machine learning group and data management group. Students are required to present a selected topic.
Example topics are
- Alignment of Multi-modal Data
- Compression in ML Systems
- Data Augmentation and Distillation
- Data Cleaning for ML
- Federated Data Preparation and Learning
- Sparsity Exploitation in ML Systems
- Model Debugging, Bias, Fairness
- Deep generative models
- Parallel computation
- Hashing and sketches
- Auto ML
- Scalable Bayesian Learning
- Random features
- Optimization
- Stochastic/online methods
- Ensemble learning
- Dimensionality reduction/Visualization