RESEARCH PAPERYear 2017

Neural Discrete Representation Learning

Aaron van den Oord; Oriol Vinyals; Koray Kavukcuoglu

Classification

View four quadrants
Major category
Components of WAMs
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. VQ-VAE explicitly supplies an encoder, nearest-codebook quantizer and decoder for reusable discrete representations. Its codebook/tokenization interface directly matches the manuscript visual/action-tokenizer component discussion. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX