I like how specifically this relates to my experience with the discount factor gamma in Reinforcement Learning. Like, pretty close to the exact numbers (though missing 0.99 and 0.999)
this post was submitted on 26 Mar 2024
377 points (96.5% liked)
Programmer Humor
23177 readers
1304 users here now
Welcome to Programmer Humor!
This is a place where you can post jokes, memes, humor, etc. related to programming!
For sharing awful code theres also Programming Horror.
Rules
- Keep content in english
- No advertisements
- Posts must be related to programming or programmer topics
founded 2 years ago
MODERATORS
Your neural network just learned to flawlessly answer any question you send it! Time to put it to good use!
Start asking the important questions!
Is this overfitting?
No, this is because the testing set can be derived from the training set.
Overfitting alone can't get you to 1.
It can if you don't do a train-test split.
But even if you consider the training set only, having zero loss is definitely a bad sign.
So as an eli5, that's basically that you have to "ask" it stuff it has never heard before? AI has come after my time in higher education.
Yes, it's called a train test split, and is often 80/20 or there about
Yes.
You train it on some data, and ask it about different data. Otherwise it just hard-codes the answers.
Gotcha, thank you!
They're just like us.
Gotcha!
Have you tried some data augmentation?