Reducing the Dimensionality of Data with Neural Networks Export

@article{citeulike:778023, abstract = {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. 10.1126/science.1127647}, author = {Hinton, G. E. and Salakhutdinov, R. R.}, citeulike-article-id = {778023}, citeulike-linkout-0 = {http://dx.doi.org/10.1126/science.1127647}, citeulike-linkout-1 = {http://www.sciencemag.org/content/313/5786/504.abstract}, citeulike-linkout-2 = {http://www.sciencemag.org/content/313/5786/504.full.pdf}, citeulike-linkout-3 = {http://www.sciencemag.org/cgi/content/abstract/313/5786/504}, citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/16873662}, citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=16873662}, day = {28}, doi = {10.1126/science.1127647}, journal = {Science}, keywords = {dimensionality-reduction, machine-learning, neural-networks}, month = {July}, number = {5786}, pages = {504--507}, posted-at = {2009-11-07 22:15:50}, priority = {2}, title = {Reducing the Dimensionality of Data with Neural Networks}, url = {http://dx.doi.org/10.1126/science.1127647}, volume = {313}, year = {2006} }

TY - JOUR ID - citeulike:778023 L3 - citeulike-article-id:778023 N2 - 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. 10.1126/science.1127647 IS - 5786 JF - Science EP - 507 TI - Reducing the Dimensionality of Data with Neural Networks VL - 313 SP - 504 KW - dimensionality-reduction KW - machine-learning KW - neural-networks AU - Hinton, GE AU - Salakhutdinov, RR PY - 2006/07/28/ UR - http://dx.doi.org/10.1126/science.1127647 ER -