{"id":"W4386570240","doi":"10.1016/j.patcog.2023.109954","title":"Training feedforward neural nets in Hopfield-energy-based configuration: A two-step approach","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Mitacs","keywords":"Computer science; Artificial intelligence; Artificial neural network; Cluster analysis; Minification; Entropy (arrow of time); Feed forward; Unsupervised learning; Intuition; Machine learning; Hopfield network; Feedforward neural network; Energy minimization; Energy (signal processing); Pattern recognition (psychology); Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007321223,0.000741331,0.0008154025,0.0004688246,0.0004522782,0.0007351713,0.001785688,0.001900862,0.005099417],"category_scores_gemma":[0.001987837,0.0006531918,0.0005170462,0.0004715282,0.0004184711,0.001031765,0.001157915,0.001084546,0.0009147906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004366246,"about_ca_system_score_gemma":0.0008233869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003663664,"about_ca_topic_score_gemma":0.006384312,"domain_scores_codex":[0.9997645,0.00006039695,0.00002307293,0.00005093689,0.00006263977,0.0000383416],"domain_scores_gemma":[0.9994079,0.0003137549,0.00002557643,0.0000720907,0.0001508814,0.00002979377],"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":[0.0002426875,0.0001521096,0.0009603092,0.0001538317,0.00009197053,0.0001724645,0.00006807569,0.7497874,0.01001107,0.004857135,0.001143048,0.2323598],"study_design_scores_gemma":[0.00001253919,0.00005242789,0.0001264423,0.00001080574,0.00001263221,0.0000218007,0.000009767419,0.9960062,0.001945187,0.001586082,0.0002094725,0.000006692364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04480752,0.0003488693,0.9487363,0.0001377439,0.00006330912,0.000160461,0.00006962397,0.0008379896,0.004838109],"genre_scores_gemma":[0.5550409,0.0001953537,0.4374751,0.0001755842,0.000048035,0.0003515221,0.0002792481,0.0001231536,0.006311259],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005099417,"threshold_uncertainty_score":0.01705927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08004302281945373,"score_gpt":0.2755046682160517,"score_spread":0.195461645396598,"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."}}