Towards Data Science cover image

104. Ken Stanley - AI without objectives

Towards Data Science

CHAPTER

The Problem With Objective Functions in Machine Learning?

In machine learning, usually we think about things in terms of setting objective. But there's another issue though, with respect to subjective objectives. It might actually be against your interest to have an objective that you're moving towards. We don't really know how to move in that direction. So probably you're gtobe moving to a dead end or something. This is like having a nose for the interesting. And if we want a i to have great ideas we can have to, i think, capture that notion more formally.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner