Jul 24, 2018 · This technique, which we call a Variational Homoencoder (VHE), produces a hierarchical latent variable model which better utilises latent variables.

This technique, which we call a Variational Ho- moencoder (VHE), produces a hierarchical la- tent variable model which better utilises la- tent variables. We ...

In a VAE, use of a recognition network encourages learning of generative models whose structure permits accurate amortised inference.

This work develops a modification of the Variational Autoencoder in which encoded observations are decoded to new elements from the same class which ...

It also extends easily to a variety of generative model structures, including the hierarchical and factorial latent variable models shown in the paper. The code ...

Variational Homo-Encoder [23] learned to infer the posterior distribution over context for a given dataset with only a few samples. However, these two works aim ...

Duration: 15:35
Posted: Oct 4, 2018

Missing: learn | Show results with:learn

The variational homoencoder: Learning to learn high capacity generative models from few examples. LB Hewitt, MI Nye, A Gane, T Jaakkola, JB Tenenbaum. arXiv ...

The variational homoencoder: Learning to learn high capacity generative models from few examples. LB Hewitt, MI Nye, A Gane, T Jaakkola, JB Tenenbaum.