Stabilization of Image Classification Accuracy in Hybrid Quantum-Classical Convolutional Neural Network with Ensemble Learning

Oumarou, Hayatou
Siradj, Yahdi
Rizal, Randi
Candra, Fikri

Innovation in Research of Informatics (INNOVATICS)
Vol 6, No 1 (2024): March 2024

Stabilization of Image Classification Accuracy in Hybrid Quantum-Classical Convolutional Neural Network Model with Ensemble Learning. Image classification plays a significant role in various technological applications, such as object recognition, autonomous vehicles, and medical image processing. Higher accuracy in image classification implies better capabilities in recognizing and understanding visual information. To enhance image classification accuracy, a Hybrid Quantum-Classical Convolutional Neural Network (HQ-CNN) model is developed by integrating quantum and classical computing elements with ensemble learning techniques. Compared to conventional neural networks, HQ-CNN enriches feature mapping in image classification predictions. The research results with HQ-CNN using ensemble learning demonstrate impressive and stable accuracy, with the lowest deviation being 1.1037.