An Optimization Network for Matrix Inversion
Abstract
Inverse matrix calculation can be considered as an optimization. We have demonstrated that this problem can be rapidly solved by highly interconnected simple neuron-like analog processors. A network for matrix inversion based on the concept of Hopfield's neural network was designed, and implemented with electronic hardware. With slight modifications, the network is readily applicable to solving a linear simultaneous equation efficiently. Notable features of this circuit are potential speed due to parallel processing, and robustness against variations of device parameters.
Cite
Text
Jang et al. "An Optimization Network for Matrix Inversion." Neural Information Processing Systems, 1987.Markdown
[Jang et al. "An Optimization Network for Matrix Inversion." Neural Information Processing Systems, 1987.](https://mlanthology.org/neurips/1987/jang1987neurips-optimization/)BibTeX
@inproceedings{jang1987neurips-optimization,
title = {{An Optimization Network for Matrix Inversion}},
author = {Jang, Ju-Seog and Lee, Soo-Young and Shin, Sang-Yung},
booktitle = {Neural Information Processing Systems},
year = {1987},
pages = {397-401},
url = {https://mlanthology.org/neurips/1987/jang1987neurips-optimization/}
}