Menu
▾
▴
About
Neural Networks Collection
Author: Arkadi Kagan
This project implements a bunch of known Neural Networks. So far the project implements: LVQ in several variants, SOM in several variants, Hopfield network and Perceptron. Other neural network types are planned, but not implemented yet.
Network types implemented:
- Set of algorithms invented by Teuvo Kohonen in around 1980, presumable first presented by
Teuvo Kohonen, "Self-organized formation of topologically correct feature maps", Journal of Biological Cybernetics, Volume 43, Issue 1, 1982, pages: 59-69
http://dx.doi.org/10.1007/BF00337288
| Name | Description |
|---|---|
| BatchLVQ1 | Batch version of Learning Vector Quantization, marked by Kohonen as LVQ-1 |
| BatchSOM | Batch version of generic-dimension Self Organizing Maps |
| BatchSOM2d | Batch version of 2D Self Organizing Maps |
| LVQ1 | Learning Vector Quantization algorithm, marked by Kohonen as LVQ-1 |
| LVQ21 | Learning Vector Quantization algorithm, marked by Kohonen as LVQ-2.1 |
| LVQ3 | Learning Vector Quantization algorithm, marked by Kohonen as LVQ-3 |
| SOM | Generic-dimension Self Organizing Map |
| SOM2d | Two-dimensional Self Organizing Map |
| Convolution | Convolutional network |
- The first known implemented artificial model called Perceptron. This algorithm has been first presented by
Frank Rosenblatt, "The perceptron - A probabilistic model for information storage and organization in the brain", Journal of Psychological Review, Volume 65, Issue 6, November, 1958, pages: 386-408
| Name | Description |
|---|---|
| Perceptron | Following Rozenblatt description |
- Algorithm presented by
Pregenzer, M., Flotzinger, D. and Pfurtscheller, G., "Distinction Sensitive Learning Vector Quantisation - a new noise-insensitive classification method", IEEE World Congress on Computational Intelligence, Volume 5, 1994, pages: 2890-2894
http://dx.doi.org/10.1109/ICNN.1994.374690
| Name | Description |
|---|---|
| DSLVQ | Distinction Sensetive LVQ |
- Algorithm presented by
Rauber, A., Merkl, D. and Dittenbach, M., "The growing hierarchical self-organizing map: exploratory analysis of high-dimensional data", IEEE Transactions on Neural Networks, Volume 13, Issue 6, Nov 2002, pages: 1331-1341
http://dx.doi.org/10.1109/TNN.2002.804221
| Name | Description |
|---|---|
| GHSOM | Growing Hierarchical SOM |
- Algorithm first described by
Nikhil R. Pal, James C. Bezdek and Eric C.-K. Tsao, "Generalized clustering network and Kohonen’s self-organizing schemes", IEEE Transactions on Neural Networks, Volume 4, Issue 4, July 1993, pages: 549-557
http://dx.doi.org/10.1109/72.238310
| Name | Description |
|---|---|
| GLVQ | Generalized LVQ |
- Algorithm first described by
Atsushi Sato and Keiji Yamada, "Generalized Learning Vector Quantization", 1995
http://nips.djvuzone.org/djvu/nips08/0423.djvu
| Name | Description |
|---|---|
| GLVQbySY | Generalized LVQ by Sato and Yamada |
- Algorithm presented by
Ming-Feng Yeh and Kuang-Chiung Chang, "GraySOFM network for solving classification problems", Journal of Neurocomputing, Volume 67, August 2005, pages: 281-287
http://dx.doi.org/10.1016/j.neucom.2005.02.007
| Name | Description |
|---|---|
| GraySOFM | Gray SOM of a generic dimension |
- Algorithm presented by
Yi-Chung Hu, Ruey-Shun Chen, Yen-Tseng Hsu and Gwo-Hshiung Tzeng, "Grey self-organizing feature maps", Journal of Neurocomputing, Volume 48, Issue 1-4, October 2002, pages: 863-877
http://dx.doi.org/10.1016/S0925-2312(01)00677-4
| Name | Description |
|---|---|
| GreySOFM | Grey SOM of a generic dimension |
- Algorithm first presented by
Barbara Hammer and Thomas Villmann, "Generalized relevance learning vector quantization", Journal of Neural Networks, Volume 15, Issue 8-9, October-November 2002, pages: 1059-1068
http://dx.doi.org/10.1016/S0893-6080(02)00079-5
| Name | Description |
|---|---|
| GRLVQ | Generalized Relevance LVQ |
- Algorithm first presented by
Damminda Alahakoon, Saman K. Halgamuge and B. Srinivasan, "A Structure Adapting Feature Map for Optimal Cluster Representation", International Conference on Neural Information Processing, Volume 2, Issue 5, 1998, pages: 809-812
| Name | Description |
|---|---|
| GSOM | Generalized SOM |
- Algorithm first presented by
Khalid BENABDESLEM and Younes BENNANI, "An incremental SOM for Web navigation patterns clustering", International Conference on Information Technology Interfaces, Volume 1, Issue 26, 2004,
pages: 209-213
http://dx.doi.org/10.1109/ITI.2004.241604
| Name | Description |
|---|---|
| ISOM | Incremental SOM |
- Algorithm first described by
Zhou Shui-shenga, Wang Wei-wei and Zhou Li-hua, "A new technique for generalized learning vector quantization algorithm", IEEE APCCAS 2000 2000 IEEE AsiaPacific Conference on Circuits and Systems Electronic Communication Systems Cat No00EX394, Volume 24, Issue 7, 2006, pages: 339-344
| Name | Description |
|---|---|
| RevisedGLVQ | Revised GLVQ |
- Algorithm first proposed by
Martin Riedmiller and Heinrich Braun, "A direct adaptive method for faster backpropagation learning - The RPROP algorithm", IEEE International Conference on Neural Networks, Volume 1, 1993, pages: 586-591
http://dx.doi.org/10.1109/ICNN.1993.298623
| Name | Description |
|---|---|
| RPROP | Resilient Propogation |
- Algorithm has been first presented by
J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities", Proc. NatL Acad. Sci. USA, Vol. 79, pp. 2554-2558, April 1982, Biophysics
| Name | Description |
|---|---|
| Hopfield | Hopfield neural network |
The project can run in two modes: command line tool and Python 7.2 extension. Currently, Python version appears more functional, as it allows easy interaction with algorithms developed by other people.
Project Members:
- Arkadi (admin)
