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

Training classical neural networks generally requires a large number oftraining samples. Using entangled training samples, Quantum Neural Networks(QNNs) have the potential to significantly reduce the amount of trainingsamples required in the training process. However, to minimize the number ofincorrect predictions made by the resulting QNN, it is essential that thestructure of the training samples meets certain requirements. On the one hand,the exact degree of entanglement must be fixed for the whole set of trainingsamples. On the other hand, training samples must be linearly independent andnon-orthogonal. However, how failing to meet these requirements affects theresulting QNN is not fully studied. To address this, we extend the proof of theQNFL theorem to (i) provide a generalization of the theorem for varying degreesof entanglement. This generalization shows that the average degree ofentanglement in the set of training samples can be used to predict the expectedquality of the QNN. Furthermore, we (ii) introduce new estimates for theexpected accuracy of QNNs for moderately entangled training samples that arelinear dependent or orthogonal. Our analytical results are (iii) experimentallyvalidated by simulating QNN training and analyzing the quality of the QNN aftertraining.

On Reducing the Amount of Samples Required for Training of QNNs: Constraints on the Linear Structure of the Training Data