Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Hopfield Networks for Vector Quantization

: Bauckhage, Christian; Ramamurthy, Rajkumar; Sifa, Rafet


Farkaš, I. ; European Neural Network Society:
Artificial Neural Networks and Machine Learning - ICANN 2020. Proceedings. Pt.II : 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15-18, 2020
Cham: Springer Nature, 2020 (Lecture Notes in Computer Science 12397)
ISBN: 978-3-030-61615-1 (Print)
ISBN: 978-3-030-61616-8 (Online)
International Conference on Artificial Neural Networks (ICANN) <29, 2020, Online>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
01IS18038A; ML2R
Conference Paper
Fraunhofer IAIS ()

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.