|
You are here |
tiao.io | ||
| | | | |
jxmo.io
|
|
| | | | | A primer on variational autoencoders (VAEs) culminating in a PyTorch implementation of a VAE with discrete latents. | |
| | | | |
blog.fastforwardlabs.com
|
|
| | | | | The Variational Autoencoder (VAE) neatly synthesizes unsupervised deep learning and variational Bayesian methods into one sleek package. In Part I of this series, we introduced the theory and intuition behind the VAE, an exciting development in machine learning for combined generative modeling and inference-"machines that imagine and reason." To recap: VAEs put a probabilistic spin on the basic autoencoder paradigm-treating their inputs, hidden representations, and reconstructed outputs as probabilistic ... | |
| | | | |
dustintran.com
|
|
| | | | | I'm excited to announce a paper that Rajesh Ranganath, Dave Blei, andI released today on arXiv, titledDeep and Hierarchical Implicit Models. | |
| | | | |
sander.ai
|
|
| | | My solution for the Galaxy Zoo challenge using convolutional neural networks | ||