## From classical to quantum machine learning with tensor networks

## RESEARCH DIRECTIONS

## Machine learning for quantum

The first goal is to use machine learning methods for the description of many-body quantum systems. In particular, we will study transport phenomena in low dimensional many-body quantum systems with new tools that are emerging by adopting neural networks to quantum mechanical problems.

## Tensor networks for machine learning

The second goal is to use methods from many-body quantum mechanics to describe machine learning problems. We will address the problems of adversarial examples, uncertainty, and generalization from a new perspective, which is motivated by the success of tensor networks for a description of many-body quantum systems.

## Machine learning on NISQ devices

The third and most ambitious goal is to combine the knowledge from quantum mechanics and machine learning to find novel applications of noisy intermediate-scale quantum devices with significant benefits (speedups, robustness,...) with respect to the classical algorithms. We will apply a combination of successful quantum-mechanical tools and advanced machine learning tools to find useful quantum algorithms that could demonstrate applied quantum advantage.