Speaker
Description
Machine learning (ML) is now ubiquitous. Fuelled by rapid advances in computational power and data accessibility, it has become the preferred paradigm for solving problems involving pattern recognition, classification, and complex, dynamic interactions. In this talk, I discuss the role that machine learning is playing in advancing material and device fabrication, as well as quantum technologies, specifically those based on diamond and hexagonal-boron nitride. This is particularly relevant as these materials, with their optically addressable spin defects, are emerging as leading hardware platforms for solid-state quantum applications in information processing, computing and sensing. I will show how ML-based methods can be successfully applied to measure certain physical quantities with better accuracy, higher resolution and/or overall fewer data points than standard approaches based on statistical inference. I will also discuss the increasingly important role machine learning is taking in the context of material design and (quantum-based) data processing, with specific focus on both its merits and its limits.
| Keyword-1 | Diamond Spin Defects |
|---|---|
| Keyword-2 | Machine Learning |
| Keyword-3 | Quantum Sensing |