A fast fixed-point algorithm for independent component analysis
Neural Computation
Constrained locally weighted clustering
Proceedings of the VLDB Endowment
Least squares quantization in PCM
IEEE Transactions on Information Theory
Fast and robust fixed-point algorithms for independent component analysis
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Existing clustering methods makes clusters focusing on the distance of the data. Therefore, the data in the created cluster is a set of similar data. When a large number of data is clustered, make smaller much data is still in the created cluster, we want to make smaller clusters. However, the existing method often results in a different output from what the user desires. Existing methods are based on the clustering of the Euclidean distance between the data. It is necessary to consider not only the similarity of data but also the independency of data. In this paper, we propose a clustering method based on the higher-order independence of data. We show that the proposed method is valid from results of experiments using created data and benchmark data.