企业官网建设流程全解析

Neural Discrete Representation Learning

神经离散表示学习

Aaron van den Oord DeepMind avdnoord@google.com

Oriol Vinyals DeepMind vinyals@google.com

Koray Kavukcuoglu DeepMind korayk@google.com

Abstract

摘要

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector QuantisedVariational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discret