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

Quantum neural networks are expected to be a promising application innear-term quantum computing, but face challenges such as vanishing gradientsduring optimization and limited expressibility by a limited number of qubitsand shallow circuits. To mitigate these challenges, an approach usingdistributed quantum neural networks has been proposed to make a prediction byapproximating outputs of a large circuit using multiple small circuits.However, the approximation of a large circuit requires an exponential number ofsmall circuit evaluations. Here, we instead propose to distribute partitionedfeatures over multiple small quantum neural networks and use the ensemble oftheir expectation values to generate predictions. To verify our distributedapproach, we demonstrate ten class classification of the Semeion and MNISThandwritten digit datasets. The results of the Semeion dataset imply that whileour distributed approach may outperform a single quantum neural network inclassification performance, excessive partitioning reduces performance.Nevertheless, for the MNIST dataset, we succeeded in ten class classificationwith exceeding 96\% accuracy. Our proposed method not only achieved highlyaccurate predictions for a large dataset but also reduced the hardwarerequirements for each quantum neural network compared to a large single quantumneural network. Our results highlight distributed quantum neural networks as apromising direction for practical quantum machine learning algorithmscompatible with near-term quantum devices. We hope that our approach is usefulfor exploring quantum machine learning applications.

Distributed Quantum Neural Networks via Partitioned Features Encoding