{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002065992,0.0001091357,0.00008570575,0.00003111185,0.003383024,0.0002395602,0.001731854,0.00004488266,0.00000338256],"category_scores_gemma":[0.00006526912,0.000100818,0.00004435674,0.0003192325,0.0001202236,0.001375741,0.0005208855,0.0001777618,0.00006300204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001018399,"about_ca_system_score_gemma":0.00005217008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002208151,"about_ca_topic_score_gemma":0.00008621138,"domain_scores_codex":[0.9990429,0.00005428361,0.00009958918,0.0004204593,0.0000722784,0.0003105476],"domain_scores_gemma":[0.9978698,0.0001714656,0.0002388923,0.001532114,0.0001044731,0.00008321265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001447523,0.00001684677,0.01375551,0.000002161235,0.00001995054,0.0000106528,0.00004790281,0.108153,0.0002038149,0.8721002,0.002295676,0.003379758],"study_design_scores_gemma":[0.001185775,0.00009207101,0.1083024,0.00006575615,0.00005590769,0.00001203911,0.0001255661,0.6188288,0.001699821,0.2164822,0.0523739,0.0007757238],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08722863,0.000020718,0.9050396,0.001445295,0.0003421577,0.0002596395,0.000001062726,0.0001935126,0.005469357],"genre_scores_gemma":[0.9900402,0.00009215085,0.004807491,0.00005010774,0.0001836842,0.000001920579,0.000001351373,0.000008446883,0.00481469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9028115,"threshold_uncertainty_score":0.9979144,"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."}}