Dropout | one minute summary
A regularization strategy motivated by a theory of the role of sex in evolution
Published in
1 min readJul 15, 2021
The purpose of dropout is alluded to in the title of its 2014 paper by Srivastava et al: “Dropout: A Simple Way to Prevent Neural Networks from Overfitting”. It has since become one of the most popular regularization techniques.
Prerequisites: Regularization
- Why? Theoretically, a great way to make predictions with a given model is to train many versions of it separately and then average the outputs. However, this is a really computationally expensive idea.
- What? Dropout is a regularization technique that prevents overfitting by approximating training multiple different neural network architectures in parallel.
- How? During training, some hidden units are randomly ignored (“dropped out”). For each training pass, different hidden units are randomly dropped, yielding a different “thinned” network each time. This makes the network more robust by preventing units from co-adapting (correcting each other’s mistakes), and therefore helps prevent overfitting. There is no dropout during testing, and thus the weights are scaled down to compensate for more nodes being active.