3min chapter

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) cover image

What the Human Brain Can Tell Us About NLP Models with Allyson Ettinger - #483

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

CHAPTER

Machine Learning and Deep Learning

It's absolutely the case that the brain also may respond to variables that we didn't intend. Just in the same way that we can with machine learning and with n p, we can draw conclusions that are mistaken because of those other variables. For me, what i was doing was taking sentence and codings from n l p models and treating those much like the brain recordings. This is a sentence ambedding, and this was being used as input to the classifie instead. And so then the key question is, can we successfully train a classifier to do the task? If so, then we're going to conclude that the critical information for doing the task was extractable from the

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