Many image classification tasks have labels that are unchanged by rotations and reflections. Equivariant quantum neural networks incorporate such symmetries by design, but the specific benefit of symmetry is difficult to isolate. Equivariant quantum circuits are usually compared with architectures that also differ in gates, structure or size. Here, we investigate the role of invariance in a controlled setting, classifying images whose labels are invariant under the dihedral group
D4. We compare four eight-qubit models with identical encoding, circuit structure and number of trainable parameters, and equivalent dynamical Lie algebras, and benchmark invariant implementations against non-invariant ones in terms of generalization error, robustness to shortcut learning and resilience to a realistic noise model. On four binary tasks, including MNIST and two scientific data sets of galaxies and red blood cells, the invariant models trained on a few tens of images show better generalization than non-invariant ones. Invariance also makes the models immune to orientation shortcuts: when trained with a class-dependent corner watermark, the non-invariant models learn the watermark and often drop to chance level when it is moved. We show that the gain in accuracy of invariant models persists also under a realistic noise model.
Optical communication has an increasing need for security in public transmission scenarios. Here, we present a protocol for cryptographic key distribution over a public network via a photon-counting compressive imaging system with watermarking, which utilizes a watermarking technique to distribute secure keys, and uses reconstructed images for simultaneous identity authentication and tampering identification. The watermark is embedded in the rearranged compressed measurements of the object, and then the signal is transmitted through a public network. At the receiving terminal, legitimate users can easily extract the watermark as the cryptographic key by using initial keys and the variance characteristic of random measurements. Artificial tampering and attacks can be detected by accurately retrieved images. The realization of this protocol is a step forward toward practical applications, and will be beneficial for the broader fields of optical security in many ways.
The storage capacity of the conventional Hopfield network is the 0.14 times of the number of neurons(P=0.14N). Because of the huge difficulty in recognizing a large number of images or patterns, researchers are looking for new methods at all times. Quantum neural network (QNN) is a young and outlying science built upon the combination of classical neural network and quantum computing. A Quantum Hopfield neural network (QHNN) whose elements of the storage matrix are distributed in a probability way on the base of quantum linear superposition is presented for speeding up the images recognition and increasing the number of the images recognition. Contrasting to the conventional Hopfield neural network, the storage capacity of the QHNN is increased by a factor of 2N, where N is the number of neurons. Besides, the case analysis and simulation tests have been carried out for the recognition of images in this paper. The result indicates that QHNN can recognize the images or patterns effectively and its working process accords with quantum evolvement process.