{"id":"W3203627589","doi":"10.1609/aaai.v36i1.19958","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","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":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Waterloo","funders":"","keywords":"Convolutional neural network; Computer science; Kronecker product; Kronecker delta; Decomposition; Pruning; Convolution (computer science); Layer (electronics); Tensor product; Algorithm; Artificial intelligence; Pattern recognition (psychology); 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":[0.0006089232,0.0008124165,0.0004978998,0.0008137837,0.0002417043,0.0007105251,0.0006638843,0.0004152453,0.00230352],"category_scores_gemma":[0.002142236,0.0002199756,0.0004440668,0.001042593,0.0005890959,0.001612905,0.0008807682,0.001083588,0.0008848352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003836877,"about_ca_system_score_gemma":0.0007307101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001959376,"about_ca_topic_score_gemma":0.002622744,"domain_scores_codex":[0.9996093,0.00007924137,0.00003098783,0.00005492712,0.0001821755,0.00004335845],"domain_scores_gemma":[0.9993207,0.0001609068,0.00006079775,0.0002741576,0.0001551576,0.00002829095],"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":[0.0003257756,0.0001466257,0.001147825,0.0001909003,0.00007589588,0.0003711773,0.0001672281,0.3217681,0.04680615,0.07818515,0.01231785,0.5384972],"study_design_scores_gemma":[0.00001707552,0.00007175074,0.0002820314,0.00001788837,0.00001430028,0.0001506565,0.00002646211,0.9550682,0.0187549,0.02110277,0.004479878,0.00001398867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.050261,0.0006028916,0.9426177,0.0002373476,0.0001169583,0.00005428899,0.0002817778,0.001844254,0.003983828],"genre_scores_gemma":[0.5003103,0.001041218,0.4901701,0.0002537162,0.0001464147,0.0001718937,0.001438968,0.00036877,0.006098651],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00230352,"threshold_uncertainty_score":0.007705986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07785216731124393,"score_gpt":0.3236004177940165,"score_spread":0.2457482504827725,"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."}}