Making machine learning in ecology transparent and reliable: A case study from autonomous biodiversity surveys

doi:None

Title	Authors

Home

Through a case study in bioacoustic classifiers, this presentation discusses lessons learned in creating transparent and reliable machine learning algorithms for ecology. We identify three components of truly open, transparent machine learning: publicly released trained models, publicly available training data, and open-source software. We also describe two stumbling blocks to realizing reliable, generalizable results from these analyses: lack of transferability between datasets and complexities in interpretations of classifier outputs.

OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.

This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.

Create an Account Learn More Hide this message

Main content

Home

Menu

Start managing your projects on the OSF today.

Main content

Links to this project

Home

Menu

Add new wiki page

Page permissions have changed

Wiki page deleted

Connected to the collaborative wiki

Connecting to the collaborative wiki

Collaborative wiki is unavailable

Browser unsupported

Start managing your projects on the OSF today.