Transcription of Neural Discrete Representation Learning
{{id}} {{{paragraph}}}
Example: bachelor of science
Neural Discrete Representation Learning
Neural Discrete Representation LearningAaron van den useful representations without supervision remains a key challenge inmachine Learning . In this paper, we propose a simple yet powerful generativemodel that learns such Discrete representations. Our model, the Vector Quantised-Variational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: theencoder network outputs Discrete , rather than continuous, codes; and the prioris learnt rather than static. In order to learn a Discrete latent Representation , weincorporate ideas from vector quantisation (VQ). Using the VQ method allows themodel to circumvent issues of posterior collapse - where the latents are ignoredwhen they are paired with a powerful autoregressive decoder - typically observedin the VAE framework.
Figure 1: Left: A figure describing the VQ-VAE. Right: Visualisation of the embedding space. The output of the encoder z(x) is mapped to the nearest point e 2. The gradient r zL(in red) will push the encoder to change its output, which could alter the configuration in the next forward pass. During forward computation the nearest embedding z
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: