We're back with another Deep Learning explained series videos. In this video, we will learn about Regularization. Regularization is a common technique that is used to deal with overfitting in ASR. But how it works and why it helps with overfitting is sometimes hard to understand.
We go over the techniques of Regularization such as L1, L2, and Dropout regularization, learn the underlying logic of Regularization, and understand the connection between this technique and neural networks.