Quantum state discrimination using noisy quantum neural networks

Near-term quantum computers are noisy, and therefore must run algorithms with a low circuit depth qubit count. Here we investigate how noise affects neural network (QNN) for state discrimination, applicable on near-term devices as it fulfils the above criteria. We find that when simulating gradient calculation noisy device, large number of parameters is disadvantageous. By introducing new smaller ansatz overcome this limitation, QNN performs well at levels current hardware. also show networks trained higher can still converge to useful parameters. Our findings be used in applications discrimination classifiers output generative adversarial networks.