{"id":"W2915058596","doi":"10.48550/arxiv.1902.02497","title":"CHIP: Channel-wise Disentangled Interpretation of Deep Convolutional Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Discriminative model; Convolutional neural network; Artificial intelligence; Interpretation (philosophy); Machine learning; Class (philosophy); Regularization (linguistics); Pattern recognition (psychology); Deep neural networks; Deep learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002018538,0.0002554528,0.0003322505,0.0002537631,0.0000930333,0.00007688818,0.001127421,0.000212049,0.00004764355],"category_scores_gemma":[0.00003869779,0.0003022086,0.0002506494,0.0004254948,0.0001146363,0.0003963205,0.001011992,0.0005170333,0.00004258625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001372745,"about_ca_system_score_gemma":0.00008548162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003389579,"about_ca_topic_score_gemma":0.00001884733,"domain_scores_codex":[0.9983638,0.0002092211,0.0002703392,0.0007446103,0.0001263965,0.0002856383],"domain_scores_gemma":[0.9983978,0.000155632,0.0004555486,0.0006696581,0.0001897427,0.0001315874],"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":[0.00006205673,0.00004950309,0.00184745,0.000039492,0.00005948826,0.00002788873,0.0004651788,0.955489,0.000007140973,0.04076759,0.00003915399,0.001146039],"study_design_scores_gemma":[0.000530329,0.00004633596,0.004555765,0.00006112768,0.00003648497,0.000003172724,0.0001036201,0.9894356,0.000007509318,0.004899091,0.000040557,0.00028042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05688958,0.0001241735,0.9393809,0.00005703498,0.001264898,0.0002747665,0.000006226493,0.0001354761,0.001866988],"genre_scores_gemma":[0.9984162,0.00004177587,0.0006637959,0.0001231128,0.00007042973,0.000001026056,0.000062078,0.0000154392,0.0006061014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9415267,"threshold_uncertainty_score":0.999943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03622998905941067,"score_gpt":0.1854060361997821,"score_spread":0.1491760471403714,"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."}}