How to Incorporate New Pattern Pairs Without Having to Teach the Previously Acquired Pattern Pairs
Abstract
In this paper, we deal with the problem of associative memory synthesis. The particular issue that we wish to explore is the ability to store new input-output pattern pairs without having to modify the path weights corresponding to the already taught pattern pairs. The approach to the solution of this problem is via interpolation carried out in a Reproducing Kernel Hilbert Space setting. An orthogonalization procedure carried out on a properly chosen set of functions leads to the solution of the problem.
Cite
Text
Wabgaonkar and Stubberud. "How to Incorporate New Pattern Pairs Without Having to Teach the Previously Acquired Pattern Pairs." Neural Computation, 1992. doi:10.1162/NECO.1992.4.6.880Markdown
[Wabgaonkar and Stubberud. "How to Incorporate New Pattern Pairs Without Having to Teach the Previously Acquired Pattern Pairs." Neural Computation, 1992.](https://mlanthology.org/neco/1992/wabgaonkar1992neco-incorporate/) doi:10.1162/NECO.1992.4.6.880BibTeX
@article{wabgaonkar1992neco-incorporate,
title = {{How to Incorporate New Pattern Pairs Without Having to Teach the Previously Acquired Pattern Pairs}},
author = {Wabgaonkar, H. M. and Stubberud, Allen R.},
journal = {Neural Computation},
year = {1992},
pages = {880-887},
doi = {10.1162/NECO.1992.4.6.880},
volume = {4},
url = {https://mlanthology.org/neco/1992/wabgaonkar1992neco-incorporate/}
}