arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.03239cs.LGcs.AIstat.ML
收藏

关于更好地训练无限限制玻尔兹曼机

On better training the infinite restricted Boltzmann machines

National University of Defense Technology(国防科技大学)

Xuan Peng, Xunzhang Gao, Xiang Li

摘要:

无限限制玻尔兹曼机(iRBM)是经典RBM的一种扩展。它具有根据特定的训练数据自动确定隐层大小的良好性能。通过充分的培训,iRBM可以实现与经典RBM竞争的绩效。然而,学习iRBM的收敛是缓慢的,这是由于iRBM对其隐藏单元的排序敏感的事实,学习的滤波器从最左边的隐藏单元到右边缓慢地改变。为了打破相邻隐单元之间的这种依赖性,加快训练的收敛速度,提出了一种新的训练策略。所提出的训练策略的核心思想是在每一个梯度下降步骤之前对隐藏单元进行随机重组。潜在地,通过这种学习方法可以实现具有隐藏单元的不同排列的无限多个iRBM的混合,其具有与dropout类似的防止模型过拟合的效果。原始的iRBM也被修改为能够进行区分训练。为了评估我们的方法对学习收敛速度和模型泛化能力的影响,在二值化的MNIST和CalTech101 Silhouettes数据集上进行了几次实验。实验结果表明,该训练策略可以大大加快iRBM的学习速度,提高其泛化能力。

英文摘要:

The infinite restricted Boltzmann machine (iRBM) is an extension of the classic RBM. It enjoys a good property of automatically deciding the size of the hidden layer according to specific training data. With sufficient training, the iRBM can achieve a competitive performance with that of the classic RBM. However, the convergence of learning the iRBM is slow, due to the fact that the iRBM is sensitive to the ordering of its hidden units, the learned filters change slowly from the left-most hidden unit to right. To break this dependency between neighboring hidden units and speed up the convergence of training, a novel training strategy is proposed. The key idea of the proposed training strategy is randomly regrouping the hidden units before each gradient descent step. Potentially, a mixing of infinite many iRBMs with different permutations of the hidden units can be achieved by this learning method, which has a similar effect of preventing the model from over-fitting as the dropout. The original iRBM is also modified to be capable of carrying out discriminative training. To evaluate the impact of our method on convergence speed of learning and the model's generalization ability, several experiments have been performed on the binarized MNIST and CalTech101 Silhouettes datasets. Experimental results indicate that the proposed training strategy can greatly accelerate learning and enhance generalization ability of iRBMs.

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。

↑