From 87aa993678ec7cb5d5602d65ad66dfed04cda74e Mon Sep 17 00:00:00 2001 From: Joakim Rishaug Date: Wed, 20 Dec 2017 11:56:31 +0100 Subject: [PATCH] Fixed a typo in readme --- tutorials/03-advanced/variational_auto_encoder/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tutorials/03-advanced/variational_auto_encoder/README.md b/tutorials/03-advanced/variational_auto_encoder/README.md index 927ed13e..f6aceb24 100644 --- a/tutorials/03-advanced/variational_auto_encoder/README.md +++ b/tutorials/03-advanced/variational_auto_encoder/README.md @@ -1,5 +1,5 @@ # Variational Auto-Encoder -[Variational Auto-Encoder(VAE)](https://arxiv.org/abs/1312.6114) is one of the generative model. From a neural network perspective, the only difference between the VAE and the Auto-Encoder(AE) is that the latent vector z in VAE is stochastically sampled. This solves the problem that the AE learns identity mapping and can not have meaningful representations in latent space. In fact, the VAE uses [reparameterization trick](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/variational_auto_encoder/main.py#L40-L44) to enable back propagation without sampling z directly from the mean and variance. +[Variational Auto-Encoder(VAE)](https://arxiv.org/abs/1312.6114) is a generative model. From a neural network perspective, the only difference between the VAE and the Auto-Encoder(AE) is that the latent vector z in VAE is stochastically sampled. This solves the problem that the AE learns identity mapping and can not have meaningful representations in latent space. In fact, the VAE uses [reparameterization trick](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/variational_auto_encoder/main.py#L40-L44) to enable back propagation without sampling z directly from the mean and variance. #### VAE loss As in conventional auto-encoders, the VAE minimizes the reconstruction loss between the input image and the generated image. In addition, the VAE approximates z to the standard normal distribution so that the decoder in the VAE can be used for sampling in the test phase.