Deep-learning-based data page classification for holographic memory
Computer Vision and Pattern Recognition
2018-05-23 v1 Machine Learning
Neural and Evolutionary Computing
Optics
Abstract
We propose a deep-learning-based classification of data pages used in holographic memory. We numerically investigated the classification performance of a conventional multi-layer perceptron (MLP) and a deep neural network, under the condition that reconstructed page data are contaminated by some noise and are randomly laterally shifted. The MLP was found to have a classification accuracy of 91.58%, whereas the deep neural network was able to classify data pages at an accuracy of 99.98%. The accuracy of the deep neural network is two orders of magnitude better than the MLP.
Cite
@article{arxiv.1707.00684,
title = {Deep-learning-based data page classification for holographic memory},
author = {Tomoyoshi Shimobaba and Naoki Kuwata and Mizuha Homma and Takayuki Takahashi and Yuki Nagahama and Marie Sano and Satoki Hasegawa and Ryuji Hirayama and Takashi Kakue and Atsushi Shiraki and Naoki Takada and Tomoyoshi Ito},
journal= {arXiv preprint arXiv:1707.00684},
year = {2018}
}