Science2006 - Reducing the Dimensionality of Data with Neural Networks

时间:2018-06-10 03:49:46
【文件属性】:

文件名称:Science2006 - Reducing the Dimensionality of Data with Neural Networks

文件大小:416KB

文件格式:PDF

更新时间:2018-06-10 03:49:46

DeepLearning

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.


网友评论

  • 很有帮助的文档,大牛的原著啊,不错不错