{"id":"W3194952006","doi":"10.48550/arxiv.2108.06325","title":"Continual Backprop: Stochastic Gradient Descent with Persistent Randomness","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Randomness; Initialization; Computer science; Gradient descent; Stochastic gradient descent; Process (computing); Artificial intelligence; Algorithm; Artificial neural network; Mathematics; Statistics","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":[0.002615229,0.0009935962,0.00123772,0.0006421504,0.0006566284,0.001288211,0.002923515,0.002079583,0.003120867],"category_scores_gemma":[0.00750197,0.0008354162,0.0007032476,0.0006253294,0.001844355,0.00176801,0.002172177,0.002619185,0.001066681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009087728,"about_ca_system_score_gemma":0.001667455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003288097,"about_ca_topic_score_gemma":0.003604428,"domain_scores_codex":[0.9991568,0.000304329,0.00004381896,0.0001786127,0.0002380598,0.00007828019],"domain_scores_gemma":[0.997116,0.001528037,0.0002251426,0.0005537,0.0004290319,0.0001482333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002491792,0.0001758174,0.001259021,0.0001566971,0.00013071,0.0001707634,0.000105217,0.8087475,0.003167445,0.03696934,0.007527206,0.1413411],"study_design_scores_gemma":[0.00001339949,0.00002103444,0.00004139148,0.000007774699,0.000004210507,0.00001870081,0.000002802289,0.9922145,0.0005660499,0.006570275,0.000534181,0.000005750614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01499032,0.0002678855,0.9791478,0.0004034941,0.00007547917,0.0000795674,0.00006941177,0.002339223,0.002626752],"genre_scores_gemma":[0.5496067,0.0002942723,0.4404745,0.0006819107,0.0001400302,0.0004416321,0.000414574,0.0007607981,0.007185566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003288097,"threshold_uncertainty_score":0.01383084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06062449877952751,"score_gpt":0.1701160711287008,"score_spread":0.1094915723491733,"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."}}