神经网络于过拟合

Posted 2021-01-16 qkloveslife

“Small” neural network (fewer parameters; more prone to underfitting)

Computationally cheaper

"Large" neural network (more parameters; more prone to overfitting)

Computationally more expensive.

Use regularization (λ) to address overfitting.

简单的神经网络（更少的参数）容易出现欠拟合，但优点是计算简单。

复杂的神经网络（跟多参数，更复杂的结构）一般情况下意味着更好的性能，但是计算成本高，而且容易出现过拟合现象，这时需要运用正则化解决过拟合问题。