Читать книгу Machine Learning for Tomographic Imaging - Professor Ge Wang - Страница 65

In the context of neural network (also referred to as a model) based machine learning, the training data (in a general sense) used to build the final model are usually divided into three types for three inter-related purposes: training (in a specific sense), validation, and testing. The training dataset is used to estimate the model, the validation dataset is used to determine the network structure or the parameters that control the complexity of the model, and the test dataset tests the performance of the final selected optimal model. Brian D Ripley gave the definition of these three words in his classic monograph Pattern Recognition and Neural Networks (Bell and Sejnowski 1997).

1 Training set: A set of samples used for minimizing the loss function. The training set is also used to compute the gradient of the loss function and then adjust the parameters (i.e. weights) of the network.

2 Validation set: A set of samples used to evaluate the trained network and avoid overfitting. In the case of overfitting, the network will perform poorly on the validation set.If the network performs poorly on either training or validation data, we can train and validate further or modify the network architecture. Currently, there is no governing theory on training, validation, and network architectural design. Therefore, practical experience is quite important in the field of machine learning. Also, training and validation data can switch their roles as needed so that the network can be trained up to an optimal performance. Multiple training–validation cycles can be used in a network training process.

3 Testing set: A set of samples never used for training and validation. These testing samples can be processed by the network that has been well trained and validated through steps 1 and 2. The performance of the final network is characterized with the testing set.

In summary, the training set is used to train the network or determine the parameters of the model; the validation set is used for model validation, modification, or selection; and the testing set is purely used to characterize the final model.