The Recurrent Temporal Restricted Boltzmann Machine 论文

2008引用 372

Generative Adversarial Networks and Image SynthesisModel Reduction and Neural NetworksMusic and Audio Processing

人工智能 Generative Adversarial Networks and Image Synthesis Model Reduction and Neural Networks Music and Audio Processing

作者

摘要

The Temporal Restricted Boltzmann Machine (TRBM) is a probabilistic model for sequences that is able to successfully model (i.e., generate nice-looking samples of) several very high dimensional sequences, such as motion capture data and the pixels of low resolution videos of balls bouncing in a box. The major disadvan-tage of the TRBM is that exact inference is extremely hard, since even computing a Gibbs update for a single variable of the posterior is exponentially expensive. This difficulty has necessitated the use of a heuristic inference procedure, that nonetheless was accurate enough for successful learning. In this paper we intro-duce the Recurrent TRBM, which is a very slight modification of the TRBM for which exact inference is very easy and exact gradient learning is almost tractable. We demonstrate that the RTRBM is better than an analogous TRBM at generating motion capture and videos of bouncing balls. 1

作者查看全部 (3)

Graham W. Taylor

Geoffrey E. Hinton

Ilya Sutskever

The Recurrent Temporal Restricted Boltzmann Machine 论文

详细信息

摘要

作者查看全部 (3)

相关技术查看全部 (3)

相关事件

相关文章