Artificial Intelligence and Machine Learning techniques are data driven; therefore their performance depends on the relation existing among the data-points, and the data-points and the expected output. In order to evaluate the appropriateness of the application of Quantum Machine Learning techniques on real data, the target datasets should be either evaluated to find underlying relations, or define a mapping schema for defining a data representation suitable for quantum machine learning techniques.
With this project we are looking forward to study the effect of data pre-processing and data transformation in Quantum Machine Learning Techniques. This analysis will be conducted of synthetic datasets assessing the performance of already implement quantum machine learning algorithms. For this project we have formed a small study group and have found some hints that under some transformations of the datasets QML algorithms perform differently. It would be ideal if we prove and formalize this hypothesis.
Evaluation of the suitability of datasets for processing with Quantum Machine Learning and Quantum Assisted Machine Learning.
- First Meeting (March 10) - DONE!
- Mid-Term Review (April 1)
- Defined Project – 2 weeks working on project
- 3 min presentation each
- Final Showcase (June 3)