English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper proposes a novel quantum pre-processing filter (QPF) to improvethe image classification accuracy of neural network (NN) models. A simple fourqubit quantum circuit that uses Y rotation gates for encoding and twocontrolled NOT gates for creating correlation among the qubits is applied as afeature extraction filter prior to passing data into the fully connected NNarchitecture. By applying the QPF approach, the results show that the imageclassification accuracy based on the MNIST (handwritten 10 digits) and theEMNIST (handwritten 47 class digits and letters) datasets can be improved, from92.5% to 95.4% and from 68.9% to 75.9%, respectively. These improvements wereobtained without introducing extra model parameters or optimizations in themachine learning process. However, tests performed on the developed QPFapproach against a relatively complex GTSRB dataset with 43 distinct classreal-life traffic sign images showed a degradation in the classificationaccuracy. Considering this result, further research into the understanding andthe design of a more suitable quantum circuit approach for image classificationneural networks could be explored utilizing the baseline method proposed inthis paper.

Development of a Novel Quantum Pre-processing Filter to Improve Image Classification Accuracy of Neural Network Models