{"id":"W3102093079","doi":"10.48550/arxiv.2001.01969","title":"Sparse Weight Activation Training","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Memory footprint; Computer science; FLOPS; Speedup; Computation; Training (meteorology); Convergence (economics); Convolutional neural network; Reduction (mathematics); Residual neural network; Artificial neural network; Artificial intelligence; Computer engineering; Parallel computing; Machine learning; Algorithm; Mathematics","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":[0.0004680067,0.0007660902,0.0004805104,0.0004138383,0.0003087355,0.0005290799,0.001256812,0.0007711675,0.007077199],"category_scores_gemma":[0.002922545,0.0003453143,0.0003263415,0.0005766334,0.0004137119,0.001141539,0.0009763518,0.001071472,0.002214313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005246649,"about_ca_system_score_gemma":0.0009984632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003693734,"about_ca_topic_score_gemma":0.006760107,"domain_scores_codex":[0.9996763,0.00005558297,0.00001781452,0.00007250936,0.000121925,0.00005594951],"domain_scores_gemma":[0.9993073,0.0002249294,0.00006044249,0.0001416738,0.000233116,0.00003258123],"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":[0.0003224827,0.0001790208,0.003122371,0.0002240267,0.00009098146,0.0001660771,0.0001219364,0.3431673,0.02787669,0.0169943,0.02683062,0.5809042],"study_design_scores_gemma":[0.00002167707,0.00004937733,0.0003790397,0.00001343334,0.000008629338,0.00005264989,0.00001696737,0.9779503,0.01044574,0.006443585,0.004611582,0.00000698957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05916363,0.0004124987,0.9204,0.0005524969,0.0002344838,0.0001597623,0.0005022029,0.005430476,0.01314448],"genre_scores_gemma":[0.5876932,0.0003700462,0.3916515,0.0004663104,0.00009798176,0.0003424342,0.002050312,0.0006317386,0.0166964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007077199,"threshold_uncertainty_score":0.02367556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1596876820713097,"score_gpt":0.2096994079966755,"score_spread":0.05001172592536579,"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."}}