{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006463048,0.0002496514,0.0002396887,0.0001182874,0.0001644024,0.00007186194,0.001664051,0.0001726049,0.00001641275],"category_scores_gemma":[0.00002523508,0.0003090739,0.0001304876,0.0008098824,0.00006146662,0.0004727707,0.001508636,0.0006140301,0.0001299299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001480121,"about_ca_system_score_gemma":0.0001358509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001034655,"about_ca_topic_score_gemma":0.000004325705,"domain_scores_codex":[0.9982932,0.00006786983,0.00015946,0.001118551,0.00007969645,0.0002812184],"domain_scores_gemma":[0.9983666,0.0001157982,0.0002496482,0.001010035,0.0000769348,0.0001809817],"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":[0.00001297963,0.00003663528,0.0001370254,0.00002340003,0.00004241151,0.00008556605,0.0004599708,0.3041902,0.0004594086,0.688311,0.0008283205,0.005413122],"study_design_scores_gemma":[0.0002328515,0.00002120915,0.0004653617,0.00004686639,0.00002440185,0.000002606554,0.00003412951,0.743031,0.0006783887,0.2489523,0.006100508,0.0004103407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02526024,0.00001192744,0.9691547,0.001238309,0.0002587968,0.0002938856,0.0000052349,0.0005308441,0.003246041],"genre_scores_gemma":[0.9841161,0.00007324515,0.01478997,0.000363756,0.000180308,0.000002744618,0.00002193722,0.00001871074,0.0004332293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9588559,"threshold_uncertainty_score":0.9999362,"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."}}