Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, 2016 (MIT Press) - Covers fundamental concepts of generalization, overfitting, and the use of validation sets for model selection and monitoring.
Training Neural Networks Part 1: Setting up the Data and the Loss, Stanford University CS231n Course Staff, 2023 - Provides an accessible introduction to data splitting (training, validation, test sets), monitoring overfitting, and early stopping in the context of neural networks.
PyTorch Documentation, PyTorch Contributors, 2023 (PyTorch Foundation) - Official documentation describing the train() and eval() methods for nn.Module and the torch.no_grad() context manager, which are crucial for implementing training and validation loops.