Data Skeptic cover image

NLP in 2019

Data Skeptic

00:00

Machine Learning

In machine learning, we have the input, which would be maybe the english text, and the output, which is the russian text. We're talking about thousands of words. Having a fast model that could you could experiment and optimise is very important. It doesn't necessarily behave exactly like human memory, but definitely its memory. So why do you call it an internal state? What of its external, like an external hard drive? Ah, good question. Indeed, it worked el in absolute performance, it worked better than c n m.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app