Faithful Representations and Topographic Maps: From Distortion- to Information-Based Self-Organization
Self organization of a massive document collection
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
We present an approach to interpret gene profiles derived from biomedical literature using Self Organizing Maps (SOMs). Comparison of different clustering algorithms shows that SOMs perform better in grouping high dimensional gene profiles when a lot of noise is present in the data. Qualitative analysis of the clustering results prove that SOMs allow an in-depth interpretation of gene profiles with biological relevance.