TY  - CPAPER
U1  - Konferenzveröffentlichung
A1  - Villmann, Thomas
A1  - Engelsberger, Alexander
T1  - Quantum Computing for Efficient Learning in Prototype-based
Vector Quantization
T2  - 26. Interdisziplinäre Wissenschaftliche Konferenz Mittweida
N2  - Prototype-based Vector Quantization is one of the key methods in data processing like data compression or interpretable classification learning. Prototype vectors serve as references for data and data classes. The data are given as vectors representing objects by numerical features. Famous approaches are the Neural Gas Vector Quantizer (NGVQ) for data compression and Learning Vector Quantizers (LVQ) for classification tasks. Frequently, training of those models is time consuming. In the contribution we discuss modifications of these algorithms adopting ideas from quantum computing. The aim for this is a least twofold: First quantum computing provides ideas for enormous speedup making use of quantum mechanical systems and inherent parallelization.
Second, considering data and prototype vectors in terms of quantum systems, implicit data processing is performed, which frequently results in better data separation. We will highlight respective ideas and difficulties when equipping vector quantizers with quantum computing features.
KW  - Maschinelles Lernen
KW  - Quantencomputer
KW  - Vector Quantization
Y1  - 2021
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mit1-opus4-122969
SN  - 1437-7624
SS  - 1437-7624
U6  - https://doi.org/10.48446/opus-12296
DO  - https://doi.org/10.48446/opus-12296
IS  - 002
SP  - 137
EP  - 140
S1  - 4
PB  - Hochschule Mittweida
CY  - Mittweida
ER  -