首页> 外文期刊>Journal of machine learning research >Pyro: Deep Universal Probabilistic Programming
【24h】

Pyro: Deep Universal Probabilistic Programming

机译:Pyro:深度通用概率编程

获取原文
           

摘要

Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research. To scale to large data sets and high-dimensional models, Pyro uses stochastic variational inference algorithms and probability distributions built on top of PyTorch, a modern GPU-accelerated deep learning framework. To accommodate complex or model-specific algorithmic behavior, Pyro leverages Poutine, a library of composable building blocks for modifying the behavior of probabilistic programs.
机译:Pyro是一种在Python上构建的概率编程语言,作为在AI研究中开发先进概率模型的平台。 为了扩展到大数据集和高维模型,Pyro采用了在Pytorch顶部构建的随机变分推理算法和概率分布,现代GPU加速的深度学习框架。 为了适应复杂或模型特定的算法行为,Pyro利用Poutine,一个用于修改概率计划的行为的可协式构建块库。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号