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.