Avoidable bias:
(1) Train bigger model
(2) train longer/better optimization algorithms
(3) NN architecture/hyperparameters search

Variance:
(1) More data
(2) Regularization: L2, drop out, data augmentation...
(3) NN architecture/hyperparameters search

University of Michigan - Ann Arbor

1. the difference between human error and training error: avoidable bias

2. the difference between training error and dev error: variations

Avoidable bias

Improving deep learning model performance

- Train a bigger neural model.
- Train with better optimization algorithms.
- Find better neural network architecture.

Learn Before

Related