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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Machine learning methods have revolutionized the discovery process of newmolecules and materials. However, the intensive training process of neuralnetworks for molecules with ever-increasing complexity has resulted inexponential growth in computation cost, leading to long simulation time andhigh energy consumption. Photonic chip technology offers an alternativeplatform for implementing neural networks with faster data processing and lowerenergy usage compared to digital computers. Photonics technology is naturallycapable of implementing complex-valued neural networks at no additionalhardware cost. Here, we demonstrate the capability of photonic neural networksfor predicting the quantum mechanical properties of molecules. To the best ofour knowledge, this work is the first to harness photonic technology formachine learning applications in computational chemistry and molecularsciences, such as drug discovery and materials design. We further show thatmultiple properties can be learned simultaneously in a photonic chip via amulti-task regression learning algorithm, which is also the first of its kindas well, as most previous works focus on implementing a network in theclassification task.

A photonic chip-based machine learning approach for the prediction of molecular properties