{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003293275,0.0002340927,0.0002503207,0.00005736879,0.001040793,0.0001210256,0.00218572,0.00003679386,0.0001589763],"category_scores_gemma":[0.0000546372,0.0001951995,0.0001277935,0.001059454,0.0002387612,0.0005342943,0.001164247,0.0004769554,0.00003420789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001144668,"about_ca_system_score_gemma":0.00007338085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001720823,"about_ca_topic_score_gemma":0.000002504571,"domain_scores_codex":[0.9975557,0.00006243123,0.0005675325,0.0006840409,0.0006992656,0.0004310033],"domain_scores_gemma":[0.9985146,0.00009807842,0.0005119484,0.0004236945,0.0003822256,0.00006948662],"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":[0.00008464917,0.000162409,0.0001097424,0.000007898884,0.00001020619,3.953519e-7,0.0003427136,0.05010367,0.04162632,0.8890861,0.001699147,0.01676671],"study_design_scores_gemma":[0.00005993966,0.0001741127,0.0003111984,0.00004798264,0.00001296104,0.00002711289,0.00008905866,0.4708155,0.1219831,0.4037449,0.002425441,0.0003087604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5412674,0.0005674646,0.394179,0.04342689,0.00417735,0.003890849,0.00005584952,0.0006850149,0.0117502],"genre_scores_gemma":[0.9734841,0.00002835203,0.02522638,0.0006650661,0.0001998369,0.0002100622,0.000005477676,0.00001513357,0.0001655754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4853413,"threshold_uncertainty_score":0.800504,"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."}}