Hopfield Networks for Vector Quantization
We consider the problem of finding representative prototypes within a set of data and solve it using Hopfield networks. Our key idea is to minimize the mean discrepancy between kernel density estimates of the distributions of data points and prototypes. We show that this objective can be cast as a quadratic unconstrained binary optimization problem which is equivalent to a Hopfield energy minimization problem. This result is of current interest as it suggests that vector quantization can be accomplished via adiabatic quantum computing.
- Published in:
ICANN 2020: Artificial Neural Networks and Machine Learning International Conference on Artificial Neural Networks (ICANN) - Type:
Inproceedings - Authors:
C. Bauckhage, R. Ramamurthy, R. Sifa - Year:
2020
Citation information
C. Bauckhage, R. Ramamurthy, R. Sifa: Hopfield Networks for Vector Quantization, International Conference on Artificial Neural Networks (ICANN), ICANN 2020: Artificial Neural Networks and Machine Learning, 2020, https://doi.org/10.1007/978-3-030-61616-8_16, Bauckhage.etal.2020c,
@Inproceedings{Bauckhage.etal.2020c,
author={C. Bauckhage, R. Ramamurthy, R. Sifa},
title={Hopfield Networks for Vector Quantization},
booktitle={International Conference on Artificial Neural Networks (ICANN)},
journal={ICANN 2020: Artificial Neural Networks and Machine Learning},
url={https://doi.org/10.1007/978-3-030-61616-8_16},
year={2020},
abstract={We consider the problem of finding representative prototypes within a set of data and solve it using Hopfield networks. Our key idea is to minimize the mean discrepancy between kernel density estimates of the distributions of data points and prototypes. We show that this objective can be cast as a quadratic unconstrained binary optimization problem which is equivalent to a Hopfield energy...}}