What is a regularization?
Any mechanism that reduces overfitting.
regularization explained in plain English
Any mechanism that reduces overfitting. Popular types of regularization include: - L1 regularization - L2 regularization - dropout regularization - early stopping (this is not a formal regularization method, but can effectively limit overfitting) Regularization can also be defined as the penalty on a model's complexity.
Regularization is counterintuitive. Increasing regularization usually increases training loss, which is confusing because, well, isn't the goal to minimize training loss? Actually, no. The goal isn't to minimize training loss. The goal is to make excellent predictions on real-world examples. Remarkably, even though increasing regularization increases training loss, it usually helps models make better predictions on real-world examples. --- See Overfitting: Model complexity in Machine Learning Crash Course for more information.
Example
Practitioners refer to regularization when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- activation function
A function that enables neural networks to learn nonlinear (complex) relationships between features and the label.
- Backpropagation
The process that tells a neural network which internal settings caused an error and how to adjust them, working backwards through layers.
- batch
The set of examples used in one training iteration.
- batch normalization
Normalizing the input or output of the activation functions in a hidden layer.
- batch size
The number of examples in a batch.
- Bayesian neural network
A probabilistic neural network that accounts for uncertainty in weights and outputs.
- co-adaptation
An undesirable behavior in which neurons predict patterns in training data by relying almost exclusively on outputs of specific other neurons instead of relying on the network's behavior as a whole.
- convergence
A state reached when loss values change very little or not at all with each iteration.
- deep model
A neural network containing more than one hidden layer.
- depth
The sum of the following in a neural network: - the number of hidden layers - the number of output layers, which is typically 1 - the number of any embedding layers For example, a neural network with five hidden layers and one output layer has a depth of 6.