Unsupervised Learning in Neurodynamics Using the Phase Velocity Field Approach
Abstract
A new concept for unsupervised learning based upon examples in(cid:173) troduced to the neural network is proposed. Each example is con(cid:173) sidered as an interpolation node of the velocity field in the phase space. The velocities at these nodes are selected such that all the streamlines converge to an attracting set imbedded in the subspace occupied by the cluster of examples. The synaptic interconnections are found from learning procedure providing selected field. The theory is illustrated by examples.
Cite
Text
Zak and Toomarian. "Unsupervised Learning in Neurodynamics Using the Phase Velocity Field Approach." Neural Information Processing Systems, 1989.Markdown
[Zak and Toomarian. "Unsupervised Learning in Neurodynamics Using the Phase Velocity Field Approach." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/zak1989neurips-unsupervised/)BibTeX
@inproceedings{zak1989neurips-unsupervised,
title = {{Unsupervised Learning in Neurodynamics Using the Phase Velocity Field Approach}},
author = {Zak, Michail and Toomarian, Nikzad Benny},
booktitle = {Neural Information Processing Systems},
year = {1989},
pages = {583-589},
url = {https://mlanthology.org/neurips/1989/zak1989neurips-unsupervised/}
}