{"doi":"10.1126/science.1127647","title":"Reducing the Dimensionality of Data with Neural Networks","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.","journal":"Science","year":2006,"id":1394,"datarank":20.985102912665166,"base_score":9.940060532766969,"endowment":9.940060532766969,"self_citation_contribution":1.4910090799150455,"citation_network_contribution":19.49409383275012,"self_endowment_contribution":1.4910090799150455,"citer_contribution":19.49409383275012,"corpus_percentile":98.2,"corpus_rank":343,"citation_count":20744,"citer_count":187,"citers_with_citation_signal":187,"citers_with_endowment":187,"datacite_reuse_total":0,"is_dataset":false,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2006-07-28","authors":[{"id":16945,"name":"R. R. Salakhutdinov","orcid":null,"position":1,"is_corresponding":false},{"id":16946,"name":"Geoffrey E. Hinton","orcid":null,"position":2,"is_corresponding":false},{"id":16947,"name":"Ruslan Salakhutdinov","orcid":"0000-0002-3752-2756","position":3,"is_corresponding":false}],"reference_count":17,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}