Skip to content

Companion notebooks to the Competitive Neural Networks series

Notifications You must be signed in to change notification settings

starschema/competitive-neural-networks

Repository files navigation

Competitive neural networks: a gentle introduction

This set of notebooks is a companion material to my series of articles on the Starschema blog discussing competitive neural networks. Unlike error-correction neural networks, to which the feedforward backpropagation neural nets you know and love belong, competitive neural networks have an entirely different idea of what neurons do, and indeed model different brain processes (associative or Hebbian learning versus the ventral stream's gradually more complex and semantic process of understanding). While these blog posts are far from giving you the complete lowdown, they're a fun introduction to the subject.

Table of contents

Blog post Companion notebook NBViewer
1 Funderstanding competitive neural networks notebook nbviewer
2 Self-Organising Feature Maps for fun and profit notebook nbviewer
3 Growing Neural Gas models: theory and practice notebook nbviewer

References

  • Foody, Giles M. "Applications of the self-organising feature map neural network in community data analysis." Ecological Modelling 120.2-3 (1999): 97-107.

  • Kohonen, Teuvo. "Exploration of very large databases by self-organizing maps." Proceedings of International Conference on Neural Networks (ICNN'97). Vol. 1. IEEE, 1997.

  • Kohonen, Teuvo. "The self-organizing map." Proceedings of the IEEE 78.9 (1990): 1464-1480.

  • Nasrabadi, Nasser M., and Yushu Feng. "Vector quantization of images based upon the Kohonen self-organizing feature maps." Proc. IEEE Int. Conf. Neural Networks. Vol. 1. 1988.

  • AT&T Laboratories Cambridge. Olivetti Faces Dataset. Cambridge, MA, 1994.

  • Van der Walt, Stefan, et al. "scikit-image: image processing in Python." PeerJ 2 (2014): e453.

  • Kälviäinen, R. V. J. P. H., and H. Uusitalo. "DIARETDB1 diabetic retinopathy database and evaluation protocol." Medical Image Understanding and Analysis. Vol. 2007. 2007.

  • Sinthanayothin, Chanjira, et al. "Automated detection of diabetic retinopathy on digital fundus images." Diabetic Medicine 19.2 (2002): 105-112.

  • Buhmann, Joachim, and Hans Kühnel. "Complexity optimized data clustering by competitive neural networks." Neural Computation 5.1 (1993): 75-88.

  • Carpenter, Gail A. "Neural network models for pattern recognition and associative memory." Neural Networks 2.4 (1989): 243-257.

  • Fritzke, Bernd. "A growing neural gas network learns topologies." Advances in Neural Information Processing Systems. 1995.

  • Prudent, Yann, and Abdellatif Ennaji. "An incremental growing neural gas learns topologies." Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, Vol. 2. IEEE, 2005.

  • Daszykowski, Michael, Beata Walczak, and Desire L. Massart. "On the optimal partitioning of data with k-means, growing k-means, neural gas, and growing neural gas." Journal of Chemical Information and Computer Sciences 42.6 (2002): 1378-1389.

  • Holdstein, Yaron, and Anath Fischer. "Three-dimensional surface reconstruction using meshing growing neural gas (MGNG)." The Visual Computer 24.4 (2008): 295-302.

Acknowledgments

The author wishes to thank Starschema for their generous research time allowance that has made the work on these posts and notebooks possible in the first place. I'd also like to thank my wife Katie for putting up with me while I was working on this (it's been a busy few weeks)