Quantum mechanism, which has received widespread attention, is in continuous evolution rapidly. The powerful computing power and high parallel ability of quantum mechanism equip the quantum field with broad application scenarios and brand-new vitality. Inspired by nature, intelligent algorithm has always been one of the research hotspots. It is a frontier interdisciplinary subject with a perfect integration of biology, mathematics and other disciplines. Naturally, the idea of combining quantum mechanism with intelligent algorithms will inject new vitality into artificial intelligence system. This paper lists major breakthroughs in the development of quantum domain firstly, then summarizes the existing quantum algorithms from two aspects: quantum optimization and quantum learning. After that, related concepts, main contents and research progresses of quantum optimization and quantum learning are introduced respectively. At last, experiments are conducted to prove that quantum intelligent algorithms have strong competitiveness compared with traditional intelligent algorithms and possess great potential by simulating quantum computing. INDEX TERMS Quantum optimization, quantum learning, quantum evolutionary algorithm (QEA), quantum particle swarm algorithm (QPSO), quantum immune clonal algorithm (QICA), quantum neural network (QNN), quantum clustering (QC).

No abstract

No abstract

Data-driven optimization is an efficient global optimization algorithm for expensive blackbox functions. In this paper, we apply data-driven optimization algorithm to the task of change detection with synthetic aperture radar (SAR) images for the first time. We first propose an easy-to-implement threshold algorithm for change detection in SAR images based on data-driven optimization. Its performance has been compared with commonly used methods like generalized Kittler and Illingworth threshold algorithms (GKIT). Next, we demonstrate how to tune the hyper-parameter of a (previously available) deep belief network (DBN) for change detection using data-driven optimization. Extensive evaluations are carried out using publicly available benchmark datasets. The obtained results suggest comparatively strong performance of our optimized DBN-based change detection algorithm. INDEX TERMS Hyper-parameter optimization, data-driven optimization, change detection, deep belief network (DBN), synthetic aperture radar (SAR) image.

With the development of deep learning, more and more neural networks have been used in polarimetric synthetic aperture radar (PolSAR) image classification and obtain good results. As we all know, the performances of neural networks highly depend on well-designed neural architectures. Besides, the features input to neural networks also have a huge impact on the classification results. Both architecture design and feature selection are time-consuming and require human expertise. So, in this paper, we propose a neural architecture search method with feature selection (Pol-NAS) for PolSAR image classification. It can automatically search and obtain a good architecture including intra-cell, inter-cell structure and the number of layers in the search stage. Meanwhile, all the features commonly used in PolSAR data interpretation, rather than part of them, are input to the model in order to avoid selecting the size of optimal feature subset, which is a hyper-parameter and usually different for different models. Then, we propose the Feature Attention block (FA block) and redesign the stem layers by combining the FA block and the original stem layers. Thus, Pol-NAS can adaptively find the importance of each feature in the training stage by using the redesigned stem layers. With the help of Pol-NAS, we only need to prepare the data and wait for the classification results. Experimental results on three real PolSAR datasets show that the performance of Pol-NAS is better than that of state-of-theart PolSAR image classification models. The code is available at https://github.com/guangyuanLiu/Pol-NAS.