Entropy Estimation in Multi-Qutrit Systems via Variational and Classical Neural Networks
Researchers have explored entropy estimation in multi-qutrit quantum systems using both variational quantum algorithms (VQAs) and classical convolutional neural networks (CNNs). For smaller systems (up to three qutrits), VQAs showed that accuracy is mainly dependent on the number of trainable parameters. For larger systems (two to five qutrits), a CNN trained on measurement outcomes demonstrated accurate and stable predictions, with performance improving as system size increased. The CNN approach proved robust to noise and required significantly fewer measurements than full state tomography for accurate predictions in four- and five-qutrit systems. AI
IMPACT This research highlights the potential of classical neural networks to scale and improve the robustness of quantum system analysis.