01 / prediction
If you have an algorithm that's trying to follow a gradient by matching closer and closer and closer to the objective, getting a higher and higher score, you're going to get stuck in a dead end because of deception, because the things that lead to the thing you want actually don't look like the thing you want.
“If you have an algorithm that's trying to follow a gradient by matching closer and closer and closer to the objective, getting a higher and higher score, you're going to get stuck in a dead end because of deception, because the things that lead to the thing you want actually don't look like the thing you want.”
- Speaker
- Kenneth Stanley
- Publisher
- Machine Learning Street Talk