arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.09489cs.LGstat.ML
收藏

深度神经网络中的随机投影

Random Projection in Deep Neural Networks

AGH University of Science and Technology in Kraków(克拉科夫AGH科技大学)

Piotr Iwo Wójcik

摘要:

这项工作研究了深度学习方法如何从随机投影(RP)中受益,这是一种经典的线性降维方法。正如我们所发现的,我们专注于两个领域,在这两个领域中,采用RP技术可以改进深度模型:在高维数据上训练神经网络和初始化网络参数。在没有可利用结构的稀疏高维数据上训练深度神经网络(DNN)意味着网络架构的输入层具有大量权重,这通常使训练不可行。我们表明,这个问题可以解决,通过预先与输入层的权重与RP矩阵初始化的网络。我们提出了几个修改的网络架构和训练制度,使其能够有效地训练DNN与学习RP层的数据与多达数千万的输入功能和训练样本。与最先进的方法相比,具有RP层的神经网络在几个极高维的真实世界数据集上实现了具有竞争力的性能或改善了结果。RP技术的应用有利于训练深度模型的第二个领域是权重初始化。将DNN中的初始权重设置为各种RP矩阵的元素,使我们能够训练剩余的深度网络以达到更高的性能水平。

英文摘要:

This work investigates the ways in which deep learning methods can benefit from random projection (RP), a classic linear dimensionality reduction method. We focus on two areas where, as we have found, employing RP techniques can improve deep models: training neural networks on high-dimensional data and initialization of network parameters. Training deep neural networks (DNNs) on sparse, high-dimensional data with no exploitable structure implies a network architecture with an input layer that has a huge number of weights, which often makes training infeasible. We show that this problem can be solved by prepending the network with an input layer whose weights are initialized with an RP matrix. We propose several modifications to the network architecture and training regime that makes it possible to efficiently train DNNs with learnable RP layer on data with as many as tens of millions of input features and training examples. In comparison to the state-of-the-art methods, neural networks with RP layer achieve competitive performance or improve the results on several extremely high-dimensional real-world datasets. The second area where the application of RP techniques can be beneficial for training deep models is weight initialization. Setting the initial weights in DNNs to elements of various RP matrices enabled us to train residual deep networks to higher levels of performance.

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。

↑