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

Artificial neural networks are finding increasing use in astronomy, butunderstanding the limitations of these models can be difficult. We utilize astatistical method, a sensitivity probe, designed to complement establishedmethods for interpreting neural network behavior by quantifying the sensitivityof a model's performance to various properties of the inputs. We apply thismethod to neural networks trained to classify images of galaxy-galaxy stronglenses in the Dark Energy Survey. We find that the networks are highlysensitive to color, the simulated PSF used in training, and occlusion of lightfrom a lensed source, but are insensitive to Einstein radius, and performancedegrades smoothly with source and lens magnitudes. From this we identifyweaknesses in the training sets used to constrain the networks, particularlythe over-sensitivity to PSF, and constrain the selection function of thelens-finder as a function of galaxy photometric magnitudes, with accuracydecreasing significantly where the g-band magnitude of the lens source isgreater than 21.5 and the r-band magnitude of the lens is less than 19.

Exploring the interpretability of deep neural networks used for gravitational lens finding with a sensitivity probe