Memorisation and generalisation
The more complex you make the model, the lower the training error always goes. But the real error? Fail to measure it and you will be fooled.
4 steps
115 XP
A free account is needed
Start the lesson →
Sources
- Geman, Bienenstock, Doursat 1992 · Neural Networks and the Bias/Variance Dilemma · Neural Computation, 4(1)
- Hastie, Tibshirani, Friedman 2009 · The Elements of Statistical Learning, Bölüm 7 · Springer
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons