Noter i Anvendt Machine learning – Optimization and regularization – 15/10 2021
Memorising = overfitting. Large neural networks are tendent to overfit. And that is to be avoided. Trade off between model and data Regularization: to change data in a way that aids in avoiding overfitting. flatten can be used on data that is flattend, but is not necesary. When overfitting, it is because it has the…