新科学想法 › 学术文库 › 学术文献 › 浏览文献

Deep learning and the renormalization group

zqyin 添加于 2014-12-18 10:17 | 1175 次阅读 | 0 个评论

作者
Bény C
摘要
Renormalization group (RG) methods, which model the way in which the effective behavior of a system depends on the scale at which it is observed, are key to modern condensed-matter theory and particle physics. We compare the ideas behind the RG on the one hand and deep machine learning on the other, where depth and scale play a similar role. In order to illustrate this connection, we review a recent numerical method based on the RG---the multiscale entanglement renormalization ansatz (MERA)---and show how it can be converted into a learning algorithm based on a generative hierarchical Bayesian network model. Under the assumption---common in physics---that the distribution to be learned is fully characterized by local correlations, this algorithm involves only explicit evaluation of probabilities, hence doing away with sampling.
详细资料
- 关键词: quant-ph
- 文献种类: Manual Script
- 期卷页: 2013年
- 日期: 2013-3-14
- 发布方式: arXiv e-prints
- 备注:arXiv:1301.3124v4
学科领域自然科学 » 物理学
相关链接 URL
zqyin 的文献笔记订阅