...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Bulletin of the American Physical Society >APS -APS March Meeting 2017 - Event - Quantum-assisted learning of graphical models with arbitrary pairwise connectivity
【24h】

APS -APS March Meeting 2017 - Event - Quantum-assisted learning of graphical models with arbitrary pairwise connectivity

机译：APS -APS 3月会议2017 - 事件 - Quantum辅助学习具有任意成对连接的图形模型

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Mainstream machine learning techniques rely heavily on sampling from generally intractable probability distributions. There is increasing interest in the potential advantages of using quantum computing technologies as sampling engines to speedup these tasks. However, some pressing challenges in state-of-the-art quantum annealers have to be overcome before we can assess their actual performance. The sparse connectivity, resulting from the local interaction between quantum bits in physical hardware implementations, is considered the most severe limitation to the quality of constructing powerful machine learning models.Here we show how to surpass this `curse of limited connectivity' bottleneck and illustrate our findings by training probabilistic generative models with arbitrary pairwise connectivity on a real dataset of handwritten digits and two synthetic datasets in experiments with up to $940$ quantum bits. Our model can be trained in quantum hardware without full knowledge of the effective parameters specifying the corresponding Boltzmann-like distribution. Therefore, the need to infer the effective temperature at each iteration is avoided, speeding up learning, and the effect of noise in the control parameters is mitigated, improving accuracy.
机译：主流机器学习技术严重依赖于通常棘手的概率分布的抽样。使用量子计算技术作为采样引擎加速这些任务的采样发动机的潜在优势越来越兴趣。然而，在我们评估其实际表现之前，必须克服最先进的量子退火者中的一些压迫挑战。由物理硬件实现中量子位之间的局部交互产生的稀疏连接被认为是对构建强大的机器学习模型的质量的最严重的限制。我们展示了如何超越这一“有限连接”瓶颈的诅咒并说明我们的通过培训具有任意成对连接的概率生成模型，在手写数字的实际数据集和两个合成数据集中的实验中的实验中具有高达940美元的量子位。我们的模型可以在Quantum硬件中培训，无需全面了解指定相应的Boltzmann样分布的有效参数。因此，避免了在每次迭代时推断有效温度的需要，加速学习，减轻控制参数中的噪声的效果，提高精度。

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