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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Quantum neural networks represent a new machine learning paradigm that hasrecently attracted much attention due to its potential promise. Under certainconditions, these models approximate the distribution of their dataset with atruncated Fourier series. The trigonometric nature of this fit could result inangle-embedded quantum neural networks struggling to fit the non-harmonicfeatures in a given dataset. Moreover, the interpretability of neural networksremains a challenge. In this work, we introduce a new, interpretable class ofhybrid quantum neural networks that pass the inputs of the dataset in parallelto 1) a classical multi-layered perceptron and 2) a variational quantumcircuit, and then the outputs of the two are linearly combined. We observe thatthe quantum neural network creates a smooth sinusoidal foundation base on thetraining set, and then the classical perceptrons fill the non-harmonic gaps inthe landscape. We demonstrate this claim on two synthetic datasets sampled fromperiodic distributions with added protrusions as noise. The training resultsindicate that the parallel hybrid network architecture could improve thesolution optimality on periodic datasets with additional noise.

Parallel Hybrid Networks: an interplay between quantum and classical neural networks