Hard threshold vs soft threshold
Why decision trees cannot be trained with gradient descent, and how a single change makes it possible. The idea the neural-trees library rests on.
5 steps
215 XP
A free account is needed
Start the lesson →
Sources
- İrsoy, Yıldız, Alpaydın 2012 · Soft Decision Trees · ICPR 2012, 1819–1822
- Frosst, N. & Hinton, G. 2017 · Distilling a Neural Network Into a Soft Decision Tree · arXiv:1711.09784
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons