3min chapter

The Gradient: Perspectives on AI cover image

Been Kim: Interpretable Machine Learning

The Gradient: Perspectives on AI

CHAPTER

Sanity Check for a Sanity and C Map Paper

In the Sanity Check for a Sanity and C map paper, we show that explanations from these two networks are visually indistinguishable to humans. The activations I see between the random network and the train network, which as you said, brings in trouble. There's so many dimensions along which I might need to stress test a piece of code. And if I miss any one of those, I kind of risk putting a product or a piece of software out there that just fails in particular instances.

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