Entanglement assisted training algorithm for supervised quantum classifiers

Abstract

We propose a new training algorithm for supervised quantum classifiers. Here, we have harnessed the property of quantum entanglement to build a model that can simultaneously manipulate multiple training samples along with their labels. Subsequently a Bell-inequality based cost function is constructed, that can encode errors from multiple samples, simultaneously, in a way that is not possible by any classical means. We show that upon minimizing this cost function one can achieve successful classification in benchmark datasets. The results presented in this paper are for binary classification problems. Nevertheless, the analysis can be extended to multi-class classification problems as well.

7 pages, 3 figures, new arguments added

References in corpus (9)

• Evaluating analytic gradients on quantum hardware
• Efficient Learning for Deep Quantum Neural Networks
• The quest for a Quantum Neural Network
• Data re-uploading for a universal quantum classifier
• Quantum Data Fitting
• Transfer learning in hybrid classical-quantum neural networks
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Supervised learning with a quantum classifier using a multi-level system
• Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits