{"id":"W3087924192","doi":"10.1007/978-3-030-58577-8_6","title":"Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Backpropagation; Convolutional neural network; Inference; Convolution (computer science); Artificial intelligence; Block (permutation group theory); Baseline (sea); Code (set theory); Artificial neural network; Machine learning; Pattern recognition (psychology); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004513094,0.0004980882,0.0004993731,0.0007247615,0.0001742971,0.0002310016,0.002672443,0.0003044257,0.00001454461],"category_scores_gemma":[0.000048756,0.0005224942,0.0001133714,0.001680016,0.0003830271,0.0008429656,0.001068548,0.001195093,0.00003096162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00046455,"about_ca_system_score_gemma":0.0002143931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001215,"about_ca_topic_score_gemma":0.0002345452,"domain_scores_codex":[0.9958826,0.0000630112,0.0007425264,0.001805918,0.0008178346,0.0006881356],"domain_scores_gemma":[0.997943,0.0004985371,0.0003162677,0.0009244917,0.0001422172,0.0001754987],"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":[0.000008941992,0.00003019905,0.000165167,0.0000139889,0.00000344402,0.000114799,0.0001209369,0.5923219,0.0001565585,0.2826572,0.00002025814,0.1243866],"study_design_scores_gemma":[0.0002386457,0.00005045714,0.001276339,0.0001015168,0.000001866353,0.00002698224,8.528946e-8,0.6453944,0.000019591,0.3524113,0.0001478304,0.0003309452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00009589321,0.0003830738,0.9931552,0.00385861,0.001345654,0.0006352247,0.000003456368,0.0001508594,0.0003720145],"genre_scores_gemma":[0.5896798,0.00006734025,0.4065288,0.002844381,0.0006390002,0.00007433074,0.00003226655,0.00004542617,0.00008861878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5895839,"threshold_uncertainty_score":0.9997227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01859235469486717,"score_gpt":0.2496386267304804,"score_spread":0.2310462720356132,"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."}}