{"id":"W3092446983","doi":"10.1609/aaai.v36i6.20611","title":"Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Initialization; Computer science; Pruning; Generalization; Artificial intelligence; Artificial neural network; Inference; Machine learning; Flow (mathematics); Sparse matrix; Lottery; Early stopping; Work flow; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003588178,0.000198531,0.0002198806,0.0001308833,0.0003077725,0.0001617659,0.001604697,0.00003855873,0.00001893756],"category_scores_gemma":[0.00008737955,0.000170951,0.00006068342,0.001006212,0.0002049422,0.0003666359,0.001062804,0.0005055804,0.000004114699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006658185,"about_ca_system_score_gemma":0.00002726795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001006683,"about_ca_topic_score_gemma":0.00001792658,"domain_scores_codex":[0.9983103,0.00003444288,0.0003222917,0.0005643009,0.0003785364,0.0003901036],"domain_scores_gemma":[0.9990908,0.0001154837,0.000263304,0.0003129446,0.0001308902,0.0000865749],"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":[0.00008441964,0.0002532054,0.001517935,0.00002152945,0.00000835221,0.000004273066,0.001906361,0.06309442,0.006080874,0.7159343,0.0004780482,0.2106163],"study_design_scores_gemma":[0.00003056917,0.0001388043,0.000686528,0.00002936675,0.000004271344,0.00001731934,0.00028884,0.9319219,0.008229821,0.05833225,0.0001335745,0.0001867473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8557464,0.000153704,0.1111116,0.02957228,0.0009180958,0.001322387,0.000008899878,0.0001824608,0.0009841148],"genre_scores_gemma":[0.99681,0.000036807,0.002392129,0.0004827568,0.00004985501,0.0001285957,6.299486e-7,0.00001215198,0.00008703284],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8688275,"threshold_uncertainty_score":0.6971179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06280376046387758,"score_gpt":0.2699841959839114,"score_spread":0.2071804355200338,"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."}}