{"id":"W3161118201","doi":"10.1109/icpr48806.2021.9412859","title":"Attention Based Pruning for Shift Networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Convolution (computer science); Inference; Pruning; Block (permutation group theory); CLs upper limits; Computation; Artificial intelligence; Function (biology); Convolutional neural network; Key (lock); Algorithm; Computer engineering; Theoretical computer science; Artificial neural network; 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":[0.0001634481,0.0002102878,0.0002216277,0.00006007142,0.0001621543,0.0003254301,0.001039533,0.0001890265,0.00001281439],"category_scores_gemma":[0.00002141361,0.0002182039,0.0001955751,0.000270009,0.00002130814,0.0001897766,0.001066442,0.0003616566,0.000004461274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005810594,"about_ca_system_score_gemma":0.0001061031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005897758,"about_ca_topic_score_gemma":0.00002223753,"domain_scores_codex":[0.9983776,0.00004333088,0.0002825256,0.0008316221,0.0001582919,0.0003066087],"domain_scores_gemma":[0.9981716,0.000237399,0.0001907534,0.001189758,0.0001274805,0.00008300744],"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":[0.000003158379,0.00005602626,0.0001416989,0.00006295192,0.00002182845,0.00000311799,0.0000306751,0.902756,0.00008963728,0.06293324,0.001408258,0.03249346],"study_design_scores_gemma":[0.0001386443,0.00001156408,0.0008460603,0.00007100652,0.0000109255,9.074986e-7,0.000003319377,0.9885041,0.0001260618,0.008217713,0.00182452,0.0002452229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005297496,0.0001747771,0.9942822,0.002504169,0.000691719,0.0008049214,0.000002392543,0.0004678128,0.0005422288],"genre_scores_gemma":[0.3528075,0.00001475428,0.6450804,0.0007718803,0.0002277046,0.0006529228,0.0001572628,0.00002045228,0.0002670731],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3522777,"threshold_uncertainty_score":0.8898095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03013004999378101,"score_gpt":0.2885999547064105,"score_spread":0.2584699047126295,"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."}}