Reducing the dimensionality of data with neural networks
Reducing the dimensionality of data with neural networks
复制标题
DOI：
10.1126/science.1127647
复制
发表时间：
2006-07-28
期刊：
影响因子：
56.9
通讯作者：
Salakhutdinov, R. R.
中科院分区：
文献类型：
--
作者：
Hinton, G. E.;Salakhutdinov, R. R.
通过训练一个具有较小中心层的多层神经网络来重构高维输入向量，可以将高维数据转换为低维代码。梯度下降可以用于微调这种“自动编码器”网络中的权重，但只有当初始权重接近一个好的解决方案时，这才能很好地工作。我们描述了一种初始化权重的有效方法，该方法允许深度自动编码器网络学习低维代码，该代码比主成分分析更好地作为降低数据维度的工具。
High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such "autoencoder'' networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.