arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1202.3748cs.LGstat.ML
收藏

结构化输出预测的条件限制Boltzmann机

Conditional Restricted Boltzmann Machines for Structured Output Prediction

University of Toronto(多伦多大学)

Volodymyr Mnih, Hugo Larochelle, Geoffrey E. Hinton

摘要:

条件限制玻尔兹曼机(CRBM)是一种丰富的概率模型,最近已被应用于广泛的问题,包括协同过滤,分类和建模运动捕捉数据。虽然在训练非条件RBM方面取得了很大进展,但这些算法不适用于条件模型,并且几乎没有关于训练和生成结构化输出问题的条件RBM预测的工作。我们首先认为,标准的基于对比发散的学习可能不适合训练CRBM。然后,我们确定两种不同类型的结构化输出预测问题,并提出了一种改进的学习算法。第一种问题类型是输出空间具有任意结构但可能的输出配置集合相对较小的问题,例如在多标签分类中。第二个问题是输出空间是任意结构的,但输出空间的可变性要大得多,例如在图像去噪或像素标记中。我们表明,新的学习算法可以更好地工作比对比发散这两种类型的问题。

英文摘要:

Conditional Restricted Boltzmann Machines (CRBMs) are rich probabilistic models that have recently been applied to a wide range of problems, including collaborative filtering, classification, and modeling motion capture data. While much progress has been made in training non-conditional RBMs, these algorithms are not applicable to conditional models and there has been almost no work on training and generating predictions from conditional RBMs for structured output problems. We first argue that standard Contrastive Divergence-based learning may not be suitable for training CRBMs. We then identify two distinct types of structured output prediction problems and propose an improved learning algorithm for each. The first problem type is one where the output space has arbitrary structure but the set of likely output configurations is relatively small, such as in multi-label classification. The second problem is one where the output space is arbitrarily structured but where the output space variability is much greater, such as in image denoising or pixel labeling. We show that the new learning algorithms can work much better than Contrastive Divergence on both types of problems.

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。

↑