Yannic Kilcher Videos (Audio Only) cover image

Neural Networks are Decision Trees (w/ Alexander Mattick)

Yannic Kilcher Videos (Audio Only)

00:00

Is There a Linearity in a Neural Network?

The decision tree essentially says with this particular input which of these relu cells am I in and at in inside of that cell it's actually a linear function. The paper shows you can rewrite the neural network and you get something like this. What does it mean? That's an entire different question because so there are many different ways of viewing such a conversion. For a position of studying decision trees it doesn't really help us that much because neural networks are inherently a lot more impenetrable than decision Trees.

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