この論文、まじで読みたい。
Reducing the Dimensionality of Data with Neural Networks
G. E. Hinton* and R. R. Salakhutdinov
http://www.sciencemag.org/cgi/content/abstract/313/5786/504
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.
この題目でサイエンスに載せることがどれだけ素晴らしいことか想像もつかない。こういうとき、手元にサイエンスを読む環境がないことが響くなー。Kに頼んでpdf送ってもらうかな、、、。