This tutorial introduces a teacher-student scheme to systematically compare different QNN architectures and to evaluate their relative expressive power. This scheme avoids training to a specific dataset and compares the learning capacity of different quantum models.
It is based on the paper " Exploring Quantum Perceptrons and Quantum Neural Networks with a teacher-student scheme" by Katerina Gratsea and Patrick Huembeli.
All code is written in Python. Libraries required with the versions used: pennylane 0.15.1, numpy 1.19.2, scikit-learn 0.23.2, matplotlib 3.3.2 .