in Studies on Deep Learning, Audio
For audio source separation task, traditional approach only utilized magnitude part ignoring phase part. Previously deep complex network provided complex arithmetics via convolution. 
Autoregressive model has been dominant model for density estimation. On the other hand, various non-linear transformations techniques enabled tracking of density after transformation of variables. Transformation Autoregressive Networks(TAN) combined non-linear transformation into autoregressive model to capture more complicated density of data.
Two approximation methods, Variational inference and MCMC, have different advantages: usually, variational inference is fast while MCMC is more accurate.
in Studies on Deep Learning, Deep Learning
Gaussian process has several advantages. Based on robust statistical assumptions, GP does not require expensive training phase and can represent uncertainty of unobserved areas. However, HP is computationally expensive. Neural process tried to combine the best of Gaussian process and neural network.
Generative models of discrete data with particular structure (grammar) often result invalid outputs. Grammar Variational Autoencoder(GVAE) forces the decoder of VAE to result only valid outputs.
VAE can learn useful representation while GAN can sample sharp images.
Learning directed generative model is difficult.
GAN had troble modeling the entire image.
Rejoice in what you learn and spray it!