Application of Neural Network based on Clustering Analysis
Haogui CHEN
Hunan City University, Yiyang, Hunan, 413000
Abstract: As the neural network clustering occurs normalization in the data inputting mode by vector and nonlinear transformation pretreatment process is easy to be filtered as a substrate for an important, but a mi-nor component of the noise, while there are still phenomenon of the drifting mode in the learning process due to the correction of the value of weight, this paper proposes an improved method of neural network. The im-proved method stores the amplitude information in the learning process, and it is considering the shortest dis-tance of being inputted into the center of the cluster, increasing a threshold limit value for determining out-liers at the same time and eliminating the influence of outliers of the clustering results. Finally, the clustering of data samples experimental results show that: the improved ART2 network can handle negative data, the four quadrants of data can be effectively clustered, the performance is superior to the traditional ART2 net-work.
Keywords: Adaptive resonance; Learning algorithm; Neurons; Resonance