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

Computational efficiency and adversarial robustness are critical factors inreal-world engineering applications. Yet, conventional neural networks oftenfall short in addressing both simultaneously, or even separately. Drawinginsights from natural physical systems and existing literature, it is knownthat an input convex architecture enhances computational efficiency, while aLipschitz-constrained architecture bolsters adversarial robustness. Byleveraging the strengths of convexity and Lipschitz continuity, we develop anovel network architecture, termed Input Convex Lipschitz Recurrent NeuralNetworks. This model outperforms existing recurrent units across a spectrum ofengineering tasks in terms of computational efficiency and adversarialrobustness. These tasks encompass a benchmark MNIST image classification,real-world solar irradiance prediction for Solar PV system planning at LHTHoldings in Singapore, and real-time Model Predictive Control optimization fora chemical reactor.

Input Convex Lipschitz RNN: A Fast and Robust Approach for Engineering Tasks