Reducing the Dimensionality of Data with Neural Networks, Geoffrey E. Hinton and Ruslan R. Salakhutdinov, 2006Science, Vol. 313 (American Association for the Advancement of Science)DOI: 10.1126/science.1127647 - This seminal paper introduced the concept of using deep autoencoders for effective dimensionality reduction, laying the groundwork for how hidden layers compress data.
Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, 2016 (MIT Press) - Provides comprehensive coverage of neural network architectures, including detailed explanations of hidden layers, activation functions, and autoencoders, serving as a standard reference.
Deep Learning with Python, François Chollet, 2021 (Manning Publications) - Offers clear explanations of how neural networks, including autoencoders, function, with a focus on practical implementation and the role of hidden layers in learning compressed representations.
Lecture 3: Neural Networks, Backpropagation and Training, MIT 6.S191 Course Staff, 2021 (MIT) - This lecture from a leading university course explains the fundamental concepts of neural networks, including hidden layers, neurons, and activation functions, which are central to encoder design.