Considering audio and image data as having quantum nature (data are represented by density matrices), we achieved better results on training architectures such as 3-layer stacked LSTM and HMM by mixing training samples using superposition augmentation and compared with plain default training and mix-up augmentation. This augmentation technique originates from the mix-up approach but provides more solid theoretical reasoning based on quantum properties. We achieved 3% improvement (from 68% to 71%) by using 38% lesser number of training samples in Russian audio-digits recognition task and 7,16% better accuracy than mix-up augmentation by training only 500 samples using HMM on the same task. Also, we achieved 1.1% better accuracy than mix-up on first 900 samples in MNIST using 3-layer stacked LSTM.
@article{arxiv.1910.10881,
title = {Superposition as Data Augmentation using LSTM and HMM in Small Training Sets},
author = {Akilesh Sivaswamy and Evgeny Pavlovskiy},
journal= {arXiv preprint arXiv:1910.10881},
year = {2019}
}
Comments
Presented on the Quantum Techniques in Machine Learning, 20-24 Oct. 2019, Daejeon, South Korea