Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, 2016 (MIT Press) - Provides theoretical background on neural networks, covering activation functions, their mathematical properties, and applications.
Rectified Linear Units Improve Restricted Boltzmann Machines, Vinod Nair, Geoffrey E. Hinton, 2010Proceedings of the 27th International Conference on Machine Learning (ICML-10) (International Conference on Machine Learning (ICML))DOI: 10.5555/3104322.3104425 - Introduces and evaluates the Rectified Linear Unit (ReLU) as an activation function, demonstrating its effectiveness.
Activations, Keras team, 2023 - Official documentation for Keras activation layers, detailing their usage and available functions.