A Dual Autoencoder Approach Using Trainable Encoding Circuits for Optimizing Quantum Neural Networks

This research presents a Dual Quantum-Traditional Auto encoder network designed for near-term quantum processors. This Dual AE consists of a variational Auto encoder and decoder network which are processed and trained using a minimal computer. In the encoding stage quantum circuits and angle based encoding method is utilized for implementation. Further the decoder model is implemented using differential two stage quantum encoding circuits. A compatible approach is developed for quantum networks thereby providing control over the accuracy balance and complexity of the circuit mechanism. By using this compatible approach scalability of the model can be improved and more qubits can be concerned in dataset dimensions. Models’ loss function is obtained for the implementation for quantum circuits in order to eliminating the need for more auxiliary bits. IBM Qis Kit development kit is utilized for simulating the process. However, a traditional computer is used for training and testing the variational auto encoder model by using Ada grad optimization algorithm. A dual traditional-quantum method is implemented using a four-stage network with varying qubit system. Proposed method is tested and the obtained results shows that the model achieve optimal performance which includes 68 gates and various trainable parameters. Minimal divergence is obtained between real data when compared with generated ones.