{"id":"W3127078660","doi":"10.1109/icassp39728.2021.9414645","title":"Pruning of Convolutional Neural Networks using ising Energy Model","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Pruning; Computer science; Redundancy (engineering); Ising model; Deep neural networks; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Algorithm; Statistical physics","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":[0.0001030424,0.000262458,0.0003622341,0.00009988159,0.0001506735,0.0001280511,0.00108501,0.0002041559,0.000007958842],"category_scores_gemma":[0.00001307848,0.0002852945,0.0001675065,0.0004078078,0.00008594492,0.0003346073,0.003024891,0.0004569713,2.090111e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001041845,"about_ca_system_score_gemma":0.0002408829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007175784,"about_ca_topic_score_gemma":0.00001495752,"domain_scores_codex":[0.998027,0.00006796356,0.0004932266,0.0007528235,0.0003117612,0.0003471703],"domain_scores_gemma":[0.9981162,0.0001224809,0.0003821484,0.001013633,0.0002689352,0.00009660301],"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":[0.000001140031,0.00001964889,0.00002354576,0.00001040246,0.00001546147,0.000002623492,0.00003392337,0.915745,0.0007168474,0.07981981,0.00003864228,0.003573026],"study_design_scores_gemma":[0.0000713284,0.000004216508,0.0000232576,0.00007004871,0.00001242294,0.00001914289,0.000007194539,0.9886196,0.0004842446,0.0104175,0.0000187482,0.0002523258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007194854,0.0007869908,0.9906678,0.0001863585,0.000375765,0.0001151805,0.00000277399,0.00016766,0.0005026234],"genre_scores_gemma":[0.5827603,0.00003554541,0.4167517,0.0002249727,0.0001027873,0.00001372919,0.00002241123,0.0000147659,0.00007381874],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5755655,"threshold_uncertainty_score":0.9999599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04968997476252107,"score_gpt":0.2872445391990175,"score_spread":0.2375545644364965,"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."}}