Abstract—

The conceptual basics of spin glass theory are reviewed. A description of the mathematical apparatus developed for spin glasses and the model of the restricted Boltzmann machine (RBM) is presented. Optimization of the RBM learning algorithm using nongradient methods is explored. A method to extract the learning algorithm hyperparameter, temperature, has been described and used. Critical phenomena in the RBM—entropy crisis, and difference between the temperatures of the learning sample creation and processing—are studied.

中文翻译：

---

从旋转眼镜到神经网络的学习

摘要——

回顾了自旋玻璃理论的概念基础。介绍了为自旋玻璃开发的数学装置和受限玻尔兹曼机 (RBM) 模型。探索了使用非梯度方法优化 RBM 学习算法。已经描述并使用了一种提取学习算法超参数温度的方法。研究了 RBM 中的关键现象——熵危机，以及学习样本创建和处理的温度之间的差异。