{"id":"W2963684275","doi":"","title":"The Reversible Residual Network: Backpropagation Without Storing Activations","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":228,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Residual; Backpropagation; Computer science; Bottleneck; Convolutional neural network; Layer (electronics); Artificial neural network; Artificial intelligence; Scheme (mathematics); Embedded system; Algorithm; Materials science; Nanotechnology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005885162,0.00133169,0.0005184317,0.0004790784,0.0003172767,0.0006489503,0.002417633,0.0009555994,0.004450593],"category_scores_gemma":[0.001843843,0.0004095973,0.000469114,0.0004338672,0.0007812488,0.002046684,0.001106366,0.001308037,0.001834853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005429219,"about_ca_system_score_gemma":0.0009437177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005078724,"about_ca_topic_score_gemma":0.009555034,"domain_scores_codex":[0.999745,0.0000400348,0.000014411,0.00007815368,0.00008368921,0.00003882204],"domain_scores_gemma":[0.9996256,0.0001007366,0.00004531442,0.0001268162,0.00007523781,0.00002640738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006625333,0.0002512461,0.0013998,0.0003649569,0.0003161734,0.0004828279,0.0001199248,0.3186977,0.06265928,0.04022865,0.0199942,0.5548227],"study_design_scores_gemma":[0.00005892277,0.0001868094,0.0003330048,0.00003302161,0.00006574375,0.0002725962,0.00002360511,0.9310575,0.04369608,0.01310292,0.01112715,0.00004266697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06740444,0.001401224,0.9002789,0.000760352,0.0004908504,0.0001616664,0.0006085651,0.0124315,0.01646253],"genre_scores_gemma":[0.5302054,0.001054696,0.4408674,0.0005364309,0.0001522085,0.0002129703,0.001533809,0.001178437,0.02425863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005078724,"threshold_uncertainty_score":0.0148887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08967421426297045,"score_gpt":0.2203711984600375,"score_spread":0.130696984197067,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}