Data Clustering: Principal Components, Hopfield and Self-Aggregation Networks

Ding, Chris H. Q.

Data Clustering: Principal Components, Hopfield and Self-Aggregation Networks

Download BibTeX Cite

Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. Pages 479-483.

Abstract

We present a coherent framework for data clustering~ Starting with a Hopfield network, we show the solutions for several well-motivated clustering objective functions are principal components. For MinMaxCut objectives motivated for ensuring cluster balance, the solutions are the nonlinearly scaled principal components. Using scaled PCA, we generalize to multi-way clustering, constructing a self-aggregation network, where connection weights between different clusters are automatically suppressed while connection weights within same clusters are automatically enhanced.

Chris H. Q. Ding. 2003. Data Clustering: Principal Components, Hopfield and Self-Aggregation Networks. In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03. IJCAI, 479–483. https://ijcai.org/proceedings/2003/71

@inproceedings{ijcai2003p71,
  title     = {Data Clustering: Principal Components, Hopfield and Self-Aggregation Networks},
  author    = {Ding, Chris H. Q.},
  booktitle = {Proceedings of the Eighteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-03}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Georg Gottlob},
  pages     = {479--483},
  year      = {2003},
  url       = {https://ijcai.org/proceedings/2003/71},
}

TY  - CPAPER
TI  - Data Clustering: Principal Components, Hopfield and Self-Aggregation Networks
AU  - Ding, Chris H. Q.
T2  - Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2003
SP  - 479
EP  - 483
UR  - https://ijcai.org/proceedings/2003/71
ER  -