The paper covered in this module on sparsifying neural networks:

Molchanov, Dmitry, Arsenii Ashukha, and Dmitry Vetrov. " Variational Dropout Sparsifies Deep Neural Networks. "

Some other examples of successful application of Bayesian methods to deep learning:

Rezende, Danilo Jimenez, and Shakir Mohamed. " Variational inference with normalizing flows. "

Ullrich, Karen, Edward Meeds, and Max Welling. " Soft weight-sharing for neural network compression. "