A Text Classification Algorithm Based on Quantum Information

作者：Shang Songtao^*; Shi Minyong; Shang Wenqian; Hong Zhiguo

来源：11th International Conference on Natural Computation (ICNC) / 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), 2015-08-15 to 2015-08-17.

• KNN
• machine learning
• text classification
• quantum information

Text classification is one of key problems in pattern recognition. The KNN algorithm is a widely used text classification algorithm, because it is simple, valid and non-parameters. The main idea of KNN algorithm is to calculate the similarity between the new sample with unknown class label and the training samples, and choosing the class label of the highest k nearest neighbors as the new sample's class label. However, the text contains hundreds and thousands of features. The similarity computing in large numbers of vector will cost many time. In fact that, many machine learning algorithms are unable to manipulate and compute large number of vectors in high-dimensional space. Quantum computing algorithms are good at computing high-dimensional vectors in large tensor product spaces. It can provide exponential speed-up over its classical counterparts. The N-dimensional quantum vectors represent 2(N) quantum superposition states. The similarity computing on the N-dimensional vectors is also on the 2(N) quantum superposition states simultaneously. Therefore, this paper introduces a KNN algorithms based on quantum computing, which uses fidelity to compute the similarity between two quantum states. The Control-Swap Test gate is very convenient as a fidelity estimator.

• 出版日期2015
• 单位中国传媒大学