Citation, DOI & article data
Regularisation is a process of reducing the complexity of a model through the inclusion of an additional parameter as in order to reduce the overfitting of a model to the training data.
In the context of radiology, a common model type used to interpret images is the convolutional neural network. Convolutional neural networks are intrinsically regularised to an extent due to the convolution of features at each layer. In practice, this trait forces the model to weight more features with intermediate magnitude rather than few features with high magnitude.
- 1. Stephen Marsland. Machine Learning. (2018) ISBN: 9781420067187
- 2. Goodfellow Ian, Yoshua Bengio and Aaron Courville. Deep learning. Cambridge, MA: The MIT Press, 2017.