| ... | ... | @@ -43,14 +43,35 @@ The Orga Team is by no means a closed circle, new members are welcome at any tim |
|
|
|
|
|
|
|
## Next Meeting
|
|
|
|
|
|
|
|
### September
|
|
|
|
tbd
|
|
|
|
|
|
|
|
### October 16: Quantum ML meets Image Understanding
|
|
|
|
|
|
|
|
*Toward quantum advantage in practically significant problems: with applications in processing satellite images and Earth observation *
|
|
|
|
|
|
|
|
Invited talk by Soronzonbold Otgonbaatar, DLR
|
|
|
|
|
|
|
|
details tbd
|
|
|
|
**Abstract:**
|
|
|
|
We first review the current state of the art of quantum computing for Earth observation and satellite images. There are the persisting challenges of profiting from quantum advantage, and finding the optimal sharing between high-performance computing (HPC) and quantum computing (QC), i.e. the HPC+QC paradigm, for computational EO problems and Artificial Intelligence (AI) approaches. Secondly, we assess some quantum models transpiled into a Clifford+T universal gate set, where the Clifford+T quantum gate set sheds light on the quantum resources required for deploying quantum models either on an HPC system or several QCs. If the Clifford+T quantum gate set cannot be simulated efficiently on an HPC system then we can apply a quantum computer and its computational power over conventional computers. Our resulting quantum resource estimation demonstrates that Quantum Machine Learning (QML) models, which do not comprise a large number of T-gates, can be deployed on an HPC system during the training and validation process; otherwise, we can execute them on several QCs. Namely, QML models having a sufficient number of T-gates provide the quantum advantage if and only if they generalize on unseen data points better than their classical counterparts deployed on the HPC system, and they break the symmetry in their weights at each learning iteration like in conventional deep neural networks. As an initial innovation, we estimate the quantum resources required for some QML models. Secondly, we define the optimal sharing between an HPC+QC system
|
|
|
|
for executing QML models for processing satellite images.
|
|
|
|
|
|
|
|
- Exploiting the Quantum Advantage for Satellite Image Processing: Quantum Resource Estimation<br>
|
|
|
|
Soronzonbold Otgonbaatar, Dieter Kranzlmüller, 2023, preprint<br>
|
|
|
|
https://arxiv.org/abs/2308.09453
|
|
|
|
|
|
|
|
- Classification of Remote Sensing Images With Parameterized Quantum Gates<br>
|
|
|
|
Soronzonbold Otgonbaatar; Mihai Datcu, 2023, IEEE Geoscience and Remote Sensing Letters<br>
|
|
|
|
https://ieeexplore.ieee.org/document/9531639
|
|
|
|
|
|
|
|
- A Quantum Annealer for Subset Feature Selection and the Classification of Hyperspectral Images<br>
|
|
|
|
Soronzonbold Otgonbaatar; Mihai Datcu, 2021, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing<br>
|
|
|
|
https://ieeexplore.ieee.org/document/9477115
|
|
|
|
|
|
|
|
- Natural Embedding of the Stokes Parameters of Polarimetric Synthetic Aperture Radar Images in a Gate-Based Quantum Computer<br>
|
|
|
|
Soronzonbold Otgonbaatar; Mihai Datcu, 2021, IEEE Transactions on Geoscience and Remote Sensing<br>
|
|
|
|
https://ieeexplore.ieee.org/document/9538388
|
|
|
|
|
|
|
|
- Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets<br>
|
|
|
|
Soronzonbold Otgonbaatar, Gottfried Schwarz, Mihai Datcu, Dieter Kranzlmüller, 2022, preprint<br>
|
|
|
|
https://arxiv.org/abs/2209.07799
|
|
|
|
|
|
|
|
## Past Meetings
|
|
|
|
|
| ... | ... | @@ -567,4 +588,4 @@ A training schedule using filter pruning and orthogonal reinitialization |
|
|
|
|
|
|
|
|
|
|
|
---
|
|
|
|
last change: 21.8.2023 sw |
|
|
\ No newline at end of file |
|
|
|
last change: 7.9.2023 sw |
|
|
\ No newline at end of file |
