Regularization

Regularization

2019/10/17

-----

// Overfitting and Regularization in Neural Networks - Ramesh Kumar - Medium

-----

Training set: A set of examples used for learning, which is to fit the parameters [i.e., weights] of the classifier.

Validation set: A set of examples used to tune the parameters [i.e., architecture, not weights] of a classifier, for example to choose the number of hidden units in a neural network.

Test set: A set of examples used only to assess the performance [generalization] of a fully specified classifier.

// [综] 训练集(train set) 验证集(validation set) 测试集(test set) - 编著人 - 博客园

-----

References

# Regularization

Moradi, Reza, Reza Berangi, and Behrouz Minaei. "A survey of regularization strategies for deep models." Artificial Intelligence Review (2019): 1-40.

https://link.springer.com/article/10.1007/s10462-019-09784-7

-----

Overfitting and Regularization in Neural Networks - Ramesh Kumar - Medium
https://medium.com/@rameshkjes/overfitting-and-regularization-in-neural-networks-d3d996e33c3

An Overview of Regularization Techniques in Deep Learning (with Python code)
https://www.analyticsvidhya.com/blog/2018/04/fundamentals-deep-learning-regularization-techniques/

A review of Dropout as applied to RNNs - Adrian G - Medium
https://medium.com/@bingobee01/a-review-of-dropout-as-applied-to-rnns-72e79ecd5b7b

-----

[综] 训练集(train set) 验证集(validation set) 测试集(test set) - 编著人 - 博客园
https://www.cnblogs.com/xfzhang/archive/2013/05/24/3096412.html 

-----