{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001477546,0.00119687,0.001309127,0.001090195,0.0007887479,0.0008535742,0.002162346,0.00165554,0.005676647],"category_scores_gemma":[0.005298348,0.0006668891,0.0006969274,0.0008575493,0.001023703,0.001977635,0.001946222,0.001794954,0.001195175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001270292,"about_ca_system_score_gemma":0.00164167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007001432,"about_ca_topic_score_gemma":0.01513023,"domain_scores_codex":[0.9992925,0.0001336623,0.00003729328,0.0001860948,0.0002446172,0.0001059039],"domain_scores_gemma":[0.9986046,0.0007319929,0.0001050278,0.0002239576,0.0002616759,0.00007277018],"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":[0.0005613568,0.0001887574,0.002423823,0.0002759444,0.0001514572,0.0002815726,0.0001820506,0.3726206,0.01520639,0.05074112,0.01453827,0.5428287],"study_design_scores_gemma":[0.00002519137,0.00005852413,0.000323824,0.00002050082,0.00002773605,0.00005157624,0.0000138006,0.9666997,0.003537396,0.02642765,0.002806074,0.000008091366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07014223,0.002387765,0.9163921,0.0007886818,0.0002102842,0.0001188081,0.0002691359,0.002668014,0.007023005],"genre_scores_gemma":[0.7118897,0.001053402,0.268307,0.001030469,0.0002890374,0.0002799921,0.001064069,0.0005433435,0.01554295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007001432,"threshold_uncertainty_score":0.01899034,"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."}}