Generalization is one of the most important issues in machine learning problems. In this study, we consider generalization in restricted Boltzmann machines (RBMs). We propose an RBM with multivalued hidden variables, which is a simple extension of conventional RBMs. We demonstrate that the proposed model is better than the conventional model via numerical experiments for contrastive divergence learning with artificial data and a classification problem with MNIST.
翻译:普遍化是机器学习问题中最重要的问题之一。 在本研究报告中,我们考虑了限制使用的波尔茨曼机器(Boltzmann machine,RBMs)的普及问题。我们提出了带有多值隐藏变量的成果管理制建议,这是传统成果管理制的简单延伸。我们证明,拟议模式比传统模式好,通过数字实验,用人工数据进行对比差异学习,并与MNIST发生分类问题。