Training Variational Quantum Circuits Using Particle Swarm Optimization

The target of this subproject will be a more efficient optimization method than the gradient descent to train a Quantum Neural Network. In particular Genetic algorithms and Particle Swarm Optimization algorithm are explored to train both the parameters and the architecture of the QNN.

KPI:

• Performane comparison with Gradient Descent optimization
• Accuracy: Ratio of correctly predicted samples to the total number of samples
• Precision: Ratio of correctly predicted positive instances to the total predicted positive instances
• Recall: Ratio of correctly predicted positive instances to all actual positive instances
• F1 Score: Harmonic mean of precision and recall