I'm referring to a specific Kaggle set: https://www.kaggle.com/c/petfinder-adoption-prediction

There are a lot of columns, and I'm (for now) ignoring the images / videos. I'm training a standard neural network, but it gets stuck very quickly. I'm happy to post my entire Keras code if it'll be helpful.

I don't understand gradient boosting, but does it somehow stop from getting stuck?

  • $\begingroup$ Is the question, essentially, what is the advantage of a gradient boosted model over a neural network? $\endgroup$ – Matthew Drury Feb 23 at 0:39
  • $\begingroup$ Yup. And if it’ll help my network from getting stuck $\endgroup$ – Shamoon Feb 23 at 12:31
  • $\begingroup$ It's a seperate predictive algorithm that has very little to do with neural networks, so it certainly won't help out your neural network training. $\endgroup$ – Matthew Drury Feb 27 at 0:07

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.