We introduce a new family of energy-based probabilistic graphical models for efficient unsupervised learning. Its definition is motivated by the control of the spin-glass properties of the Ising model described by the weights of Boltzmann machines. We use it to learn the Bars and Stripes dataset of various sizes and the MNIST dataset, and show how they quickly achieve the performance offered by standard methods for unsupervised learning. Our results indicate that the standard initialization of Boltzmann machines with random weights equivalent to spin-glass models is an unnecessary bottleneck in the process of training. Furthermore, this new family allows for very easy access to low-energy configurations, which points to new, efficient training algorithms. The simplest variant of such algorithms approximates the negative phase of the log-likelihood gradient with no Markov chain Monte Carlo sampling costs at all, and with an accuracy sufficient to achieve good learning and generalization.

我们引入了一个新的基于能量的概率图形模型系列，用于高效的无监督学习。它的定义是由控制由玻尔兹曼机的权重描述的 Ising 模型的自旋玻璃特性引起的。我们使用它来学习各种大小的 Bars and Stripes 数据集和 MNIST 数据集，并展示它们如何快速实现无监督学习标准方法提供的性能。我们的结果表明，具有与自旋玻璃模型等效的随机权重的玻尔兹曼机的标准初始化是训练过程中不必要的瓶颈。此外，这个新系列允许非常容易地访问低能量配置，这指向新的、高效的训练算法。