The traditional particle swarm optimization(PSO) and its improved version aim to tackle the single task. With the development of electronic business, online severs need to deal with a batch of requests simultaneously, i.e. multitasking. Different from the parallel computer, the implicit parallelism of PSO is fully exploited, and co-evolution theory is introduced for multitasking. In the multitasking environment, different tasks correspond to different subpopulations, and the useful information is transferred from one subpopulation to another with a certain probability. Thus, co-evolutionary PSO for multitasking(CPSOM) is proposed in this paper. To verify the effectiveness of the proposed algorithm, CPSOM is used to solve a batch of function test problems, feature selection problems and constrained engineering optimization problems. Experimental results show that the useful information can be autonomously transferred from one task to another in the CPSOM environment. Moreover, cooperation of different tasks enhance the solution quality and speed up the convergence.

Deep convolutional network is prevalent in object detection task. Region-based convolutional neural network(RCNN) bridges the gap between the classification of deep convolutional network and the object detection task well. Then the whole object detection process is aggregated into a unified deep framework by Faster-RCNN. You only look once(YOLO) and single shot multibox detector(SSD) effectively improve the efficiency of object detection. Different deep object detection frameworks are comprehensively analyzed and divided into two categories: the proposal based framework and the regression based framework. The proposal based framework is utilized to generate thousands of candidate proposals and then classification and bounding box regression are conducted on these proposals. The regression based framework outputs the bounding box position through some special iterations directly. Furthermore, the advantage for different kinds of frameworks is demonstrated through adequate experiments on the mainstream database like PASCAL_VOC and COCO. Finally, the development direction of object detection is discussed.