{"id":"W2972528742","doi":"10.1007/978-3-030-30484-3_21","title":"Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Convolutional neural network; Pruning; Artificial intelligence; Benchmark (surveying); Modularity (biology); Bridge (graph theory); Deep learning; Network structure; Pattern recognition (psychology); Machine learning","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":[0.0004357424,0.0005769341,0.0006455159,0.0004257622,0.0002728686,0.0002323129,0.003693217,0.0002760264,0.00004625501],"category_scores_gemma":[0.00007435801,0.0005473406,0.0002022622,0.0005544107,0.0009321895,0.0005640351,0.001929637,0.001481994,0.00003581405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002312448,"about_ca_system_score_gemma":0.0003434789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001641819,"about_ca_topic_score_gemma":0.00004254441,"domain_scores_codex":[0.9957488,0.00006724872,0.0007560421,0.001497745,0.001111011,0.0008191132],"domain_scores_gemma":[0.9966983,0.000837914,0.0007375347,0.001205771,0.0003289266,0.0001916082],"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":[0.00001340128,0.000008892975,0.0004996203,0.00001601185,0.000009684136,0.0000305914,0.0001127095,0.758045,0.0003133286,0.04154665,0.000009164604,0.199395],"study_design_scores_gemma":[0.000241902,0.0001731813,0.001285318,0.000192384,0.000008891961,0.0002266927,1.537053e-7,0.8097869,0.00049068,0.1867462,0.0003663765,0.0004813501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002033266,0.0009004927,0.9936636,0.0001786308,0.001971914,0.0004140818,0.000004483282,0.0001289418,0.0007045845],"genre_scores_gemma":[0.5805088,0.0000449238,0.4173475,0.0006296738,0.0009720079,0.000007531161,0.00000637837,0.00004132109,0.0004418595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5784755,"threshold_uncertainty_score":0.9996978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01566753841014424,"score_gpt":0.249089511902544,"score_spread":0.2334219734923998,"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."}}