The Worst Machine Learning Ever

The process for actually doing this its its it's complicated to describe, but ii it's fairly intuitive. What you do is you, because all these weights are involved in the calculation, you put your features in for your malwear. You go all the way forward through te deep learning or the network, then you calculate your error, and then you go backwards, adjusting the weights based on what yo've just found out esentually. And we use a process called starcastic gradient descent often to train this. So what we're doing is we're picking random our wares and putting them in, and that will of it will often get them wrong, because it's never seen any

Transcript

Play full episode

Transcript

Episode notes

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app