“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。
原文地址:https://www.cnblogs.com/qkloveslife/p/9887119.html
时间: 2024-10-01 03:48:06