neural networks research group
areas
people
projects
demos
publications
software/data
Self-Organizing Process Based On Lateral Inhibition And Synaptic Resource Redistribution (1991)
Risto Miikkulainen
Self-organizing feature maps are usually implemented by abstracting the low-level neural and parallel distributed processes. An external supervisor finds the unit whose weight vector is closest in Euclidian distance to the input vector and determines the neighborhood for weight adaptation. The weights are changed proportional to the Euclidian distance. In a biologically more plausible implementation, similarity is measured by a scalar product, neighborhood is selected through lateral inhibition and weights are changed by redistributing synaptic resources. The resulting self-organizing process is quite similar to the abstract case. However, the process is somewhat hampered by boundary effects and the parameters need to be carefully evolved. It is also necessary to add a redundant dimension to the input vectors.
View:
PDF
,
PS
Citation:
In Teuvo Kohonen and Kai M{"a}kisara and Olli Simula and Jari Kangas, editors,
Proceedings of the 1991 International Conference on Artificial Neural Networks
, 415-420, 1991. Amsterdam: North-Holland.
Bibtex:
@InProceedings{miikkulainen:selforganizing, title={Self-Organizing Process Based On Lateral Inhibition And Synaptic Resource Redistribution}, author={Risto Miikkulainen}, booktitle={Proceedings of the 1991 International Conference on Artificial Neural Networks}, editor={Teuvo Kohonen and Kai M{"a}kisara and Olli Simula and Jari Kangas}, publisher={Amsterdam: North-Holland}, pages={415-420}, url="http://nn.cs.utexas.edu/?miikkulainen:icann91", year={1991} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Areas of Interest
Visual Cortex
Computational Neuroscience
Unsupervised Learning, Clustering, and Self-Organization