Model compression plays a vital role in the practical deployment of deep neural networks (DNNs), and evolutionary multi-objective (EMO) pruning is an essential tool in balancing the compression rate and performance of the DNNs. However, due to its population-based nature, EMO pruning suffers from the complex optimization space and the resource-intensive structure verification process, especially in complex networks. To this end, a multi-objective complex network pruning framework based on divide-and-conquer and global performance impairment ranking (EMO-DIR) is proposed in this paper. Firstly, a divide-and-conquer EMO network pruning method is proposed, which decomposes the complex task of EMO pruning on the entire network into easier sub-tasks on multiple sub-networks. On the one hand, this decomposition narrows the pruning optimization space and decreases the optimization difficulty; on the other hand, the smaller network structure converges faster, so the proposed algorithm consumes lower computational resources. Secondly, a sub-network training method based on cross-network constraints is designed, which could bridge independent EMO pruning sub-tasks, allowing them to collaborate better and improving the overall performance of the pruned network. Finally, a multiple sub-networks joint pruning method based on EMO is proposed. This method combines the Pareto Fronts from EMO pruning results on multiple sub-networks through global performance impairment ranking to design a joint pruning scheme. The rich experiments on CIFAR-10/100 and ImageNet-100/1k are conducted. The proposed algorithm achieves a comparable performance with the state-of-the-art pruning methods.

We introduce several novel word features for keyword extraction and headline generation. These new word features are derived according to the background knowledge of a document as supplied by Wikipedia. Given a document, to acquire its background knowledge from Wikipedia, we first generate a query for searching the Wikipedia corpus based on the key facts present in the document. We then use the query to find articles in the Wikipedia corpus that are closely related to the contents of the document. With the Wikipedia search result article set, we extract the inlink, outlink, category and infobox information in each article to derive a set of novel word features which reflect the document's background knowledge. These newly introduced word features offer valuable indications on individual words' importance in the input document. They serve as nice complements to the traditional word features derivable from explicit information of a document. In addition, we also introduce a word-document fitness feature to charcterize the influence of a document's genre on the keyword extraction and headline generation process. We study the effectiveness of these novel word features for keyword extraction and headline generation by experiments and have obtained very encouraging results.

Personal handwritings can add colors to human communication. Handwriting, however, takes more time and is less favored than typing in the digital age. In this paper we propose an intelligent algorithm which can generate imitations of Chinese handwriting by a person requiring only a very small set of training characters written by the person. Our method first decomposes the sample Chinese handwriting characters into a hierarchy of reusable components, called character components. During handwriting generation, the algorithm tries and compares different possible ways to compose the target character. The likeliness of a given personal handwriting generation result is evaluated according to the captured characteristics of the person's handwriting. We then find among all the candidate generation results an optimal one which can maximize a likeliness estimation. Experiment results show that our algorithm works reasonably well in the majority of the cases and sometimes remarkably well, which was verified through comparison with the groundtruth data and by a small scale user survey.