Speaker
Description
In the last few decades, Quantum Computing (QC) has witnessed remarkable progress as an alternative to traditional classical computing thanks to its potential advantages in terms of representational power and computing time. This leads to extending its boundary to Quantum Machine Learning (QML), with the expectation of improving the current Machine Learning (ML) techniques to learn the hidden distribution of the dataset. However, its application on images still remains to be challenging in terms of trainability and efficiency due to the inherent non-convexity of the problem and the large dimensionality of images defined on continuous data space.
In this work, we aim to study the possible quantum algorithms to replace classical ML techniques for the classification and generation of images and explore the potential of QML in the corresponding domain.
References
.
| Keywords | Quantum Computing, Quantum Machine Learning, Machine Learning, Image analysis |
|---|
