{"id":"W2158623280","doi":"10.1162/089976600300015394","title":"Visualizing the Function Computed by a Feedforward Neural Network","year":2000,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Canada; University of British Columbia","funders":"","keywords":"Visualization; Artificial neural network; Feed forward; Feedforward neural network; Computer science; Function (biology); Probabilistic neural network; Artificial intelligence; Probabilistic logic; Activation function; Regression; Machine learning; Regression analysis; Data mining; Time delay neural network; Mathematics; Statistics; Control engineering; Engineering","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":[0.0008315516,0.001181558,0.0004649883,0.0009866345,0.0004320357,0.0012184,0.0005158148,0.0006746025,0.007794205],"category_scores_gemma":[0.003058458,0.0002688063,0.0005875506,0.0006148943,0.0004162559,0.001397034,0.0007195117,0.00104392,0.0009218174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007521022,"about_ca_system_score_gemma":0.0006648907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004358293,"about_ca_topic_score_gemma":0.002275788,"domain_scores_codex":[0.9997619,0.00008744093,0.00001525515,0.00004599156,0.00006708262,0.00002233946],"domain_scores_gemma":[0.9990616,0.0005487532,0.00005364713,0.0001024726,0.0001898069,0.00004369836],"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":[0.0003892349,0.00008616738,0.002393989,0.0004154684,0.00007776116,0.0003526669,0.0004766207,0.6387547,0.0376545,0.06955156,0.01391246,0.2359348],"study_design_scores_gemma":[0.00001591431,0.00005193774,0.000554317,0.00004712656,0.00001084597,0.00006025705,0.00005128318,0.9557526,0.007310439,0.03122616,0.004891579,0.00002745378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02451817,0.0002346156,0.9666954,0.0004036778,0.0001330412,0.00002812063,0.0003716853,0.003838649,0.003776692],"genre_scores_gemma":[0.3748443,0.0004814846,0.6175789,0.0001334317,0.00005398909,0.0001751261,0.0006113523,0.00103693,0.005084538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007794205,"threshold_uncertainty_score":0.02607423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01474548070326481,"score_gpt":0.2558216911158163,"score_spread":0.2410762104125515,"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."}}