Kernel Density Estimation with Seaton Ullberg
Rustacean Station
Using KDE to Predict the Output Target Property
Using the kernel density technique, we can generate data points within a reasonable amount of probability using this technique. So if we say that there's a region of space where it seems like we get a lot of points with these particular parameters, we can sample that really densely and build a better model. And since we started our example by saying we only had a thousand data points, we're going to do a lot more data points to train an efficient model. Not sure if I led you astray by introducing some more concepts there, but I hope that will be a little bit.
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.
