Vector quantization using k‐means clustering neural network

• Published in: Electronics letters Vol. 59; no. 7
• Main Authors: Im, Sio‐Kei, Chan, Ka‐Hou
• Format: Journal Article
• Language: English
• Published: Stevenage John Wiley & Sons, Inc 01.04.2023; Wiley
• Subjects: Algorithms; Artificial neural networks; Clustering; Data mining; Deep learning; Information theory; Machine learning; neural nets; Neural networks; Parameter modification; pattern clustering
• ISSN: 0013-5194; 1350-911X
• DOI: 10.1049/ell2.12758

Vector Quantization (VQ) is a clustering problem in the fields of signal processing, source coding, information theory etc. Taking advantage of recent advances in the field of deep neural networks, this paper investigates the performance between VQ clustering problems and deep neural networks. A k‐means‐based deep network architecture for VQ is presented to solve clustering problems. By applying the deep learning implementation of convergence optimization, a clustering neural network (algorithm) for the purpose of VQ is proposed. In practice, the proposed network quantifies the vectors over a set of stacked neural layers, overcoming the exponential complexity problem of VQ methods by trainable parameters. Experiments show that the work can improve the results without human intervention, and outperforms traditional clustering methods modified for VQ. A learnable clustering neural network is proposed for VQ tasks. The clustering center is defined as the training parameters that can achieve the traditional algorithm by deep learning approach.