Restricted Boltzmann machines are energy models made of a visible and a hidden layer. We identify an effective energy function describing the zero-temperature landscape on the visible units and depending only on the tail behaviour of the hidden layer prior distribution. Studying the location of the local minima of such an energy function, we show that the ability of a restricted Boltzmann machine to reconstruct a random pattern depends indeed only on the tail of the hidden prior distribution. We find that hidden priors with strictly super-Gaussian tails give only a logarithmic loss in pattern retrieval, while an efficient retrieval is much harder with hidden units with strictly sub-Gaussian tails; if the hidden prior has Gaussian tails, the retrieval capability is determined by the number of hidden units (as in the Hopfield model).
翻译:受限制的 Boltzmann 机器是由可见和隐藏层组成的能量模型。 我们确定一个有效的能量函数, 描述可见单位的零温度景观, 只取决于隐蔽层先前分布的尾部行为。 研究这种能量函数的本地微粒位置, 我们显示, 受限制的 Boltzmann 机器重建随机模式的能力实际上只取决于隐藏的先前分布的尾部。 我们发现, 带有严格超级Gausian尾巴的隐藏前端只会在模式检索中造成对数损失, 而有效的检索则要困难得多, 隐藏的单位则有严格的亚焦耳尾巴; 如果隐蔽的前端有高斯尾巴, 检索能力取决于隐藏单位的数量( 如Hopfield模型中的数字 ) 。