arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1011.6086stat.MLcs.LG
收藏

在所有的可能性中,只有深刻的信仰是不够的。

In All Likelihood, Deep Belief Is Not Enough

Werner Reichardt Centre for Integrative Neuroscience(维尔纳·赖卡特整合神经科学中心);Bernstein Center for Computational Neuroscience(伯恩斯坦计算神经科学中心);Max-Planck-Institute for Biological Cybernetics(马克斯·普朗克生物控制论研究所)

Lucas Theis, Sebastian Gerwinn, Fabian Sinz, Matthias Bethge

摘要:

自然刺激的统计模型为机器学习和计算神经科学领域的研究人员提供了重要的工具。一个规范的方法来定量评估和比较统计模型的性能是由可能性。最近越来越流行并已应用于各种复杂数据的一类统计模型是深度信念网络。然而,这些模型的分析,通常限于定性分析的基础上的样本,由于计算棘手的性质的模型的可能性。出于这些情况下,本文提供了一个相合估计量的可能性,这是计算上易于处理和简单的应用在实践中。使用此估计,深度信念网络,已建议自然图像补丁的建模进行定量研究,并与其他模型的自然图像补丁。与早期基于定性结果的声明相反,本文中给出的结果提供了证据,证明所研究的模型对于自然图像不是特别好的模型

英文摘要:

Statistical models of natural stimuli provide an important tool for researchers in the fields of machine learning and computational neuroscience. A canonical way to quantitatively assess and compare the performance of statistical models is given by the likelihood. One class of statistical models which has recently gained increasing popularity and has been applied to a variety of complex data are deep belief networks. Analyses of these models, however, have been typically limited to qualitative analyses based on samples due to the computationally intractable nature of the model likelihood. Motivated by these circumstances, the present article provides a consistent estimator for the likelihood that is both computationally tractable and simple to apply in practice. Using this estimator, a deep belief network which has been suggested for the modeling of natural image patches is quantitatively investigated and compared to other models of natural image patches. Contrary to earlier claims based on qualitative results, the results presented in this article provide evidence that the model under investigation is not a particularly good model for natural images

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑