Tunable Quantum Neural Networks in the QPAC-Learning Framework
This work addresses quantum machine learning challenges for researchers in quantum computing, but it is incremental as it applies existing quantum methods to a specific learning framework.
The paper tackles the problem of learning Boolean functions within the Quantum Probably Approximately Correct (QPAC) framework using tunable quantum neural networks, achieving efficient learning of concepts from a simple class through an algorithm based on amplitude amplification.
In this paper, we investigate the performances of tunable quantum neural networks in the Quantum Probably Approximately Correct (QPAC) learning framework. Tunable neural networks are quantum circuits made of multi-controlled X gates. By tuning the set of controls these circuits are able to approximate any Boolean functions. This architecture is particularly suited to be used in the QPAC-learning framework as it can handle the superposition produced by the oracle. In order to tune the network so that it can approximate a target concept, we have devised and implemented an algorithm based on amplitude amplification. The numerical results show that this approach can efficiently learn concepts from a simple class.