2min chapter

The Data Exchange with Ben Lorica cover image

Machine Learning for High-Risk Applications

The Data Exchange with Ben Lorica

CHAPTER

How to Use Machine Learning Tools to Improve Transparency

You can see a wide difference between the explanations that some tool presents, whether it's commercial or open source. You should be using explainable models and postdoc explanation, not postdoc explanation on unexplainable models. If people are using SHAP and LIME and these things on a model that's not explainable, then they should not necessarily be trusting the results.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode