{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001619187,0.0001267456,0.0001296645,0.0001587601,0.0001030405,0.0001493475,0.0002736816,0.00005536498,0.00002401944],"category_scores_gemma":[0.000007178616,0.0001277335,0.00005978281,0.0007505106,0.00001790536,0.0002708246,0.00004508278,0.0001418135,0.0000896624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001771352,"about_ca_system_score_gemma":0.00002415447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001363171,"about_ca_topic_score_gemma":0.0001486785,"domain_scores_codex":[0.9988537,0.00007248423,0.0002366787,0.0003731919,0.0001751326,0.0002888378],"domain_scores_gemma":[0.9994812,0.00009643073,0.00007938781,0.0002320294,0.00004292122,0.00006803907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000322143,0.00003479534,0.0004480225,0.000008976295,0.000003512783,0.00001349339,0.000170736,0.002588905,0.0002336912,0.0003699306,0.0009767427,0.9951479],"study_design_scores_gemma":[0.0005170945,0.00003397894,0.003232281,0.00002777464,0.000003420143,0.000009702097,0.00004954481,0.9929115,0.0004978413,0.001458301,0.001068459,0.0001900835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05869806,0.00001051369,0.9335447,0.003780131,0.0002268881,0.0002167418,0.00001074828,0.0003538292,0.003158367],"genre_scores_gemma":[0.9931017,0.000006408048,0.002937238,0.003231751,0.0001279214,0.0002493266,0.0002957688,0.00001154845,0.00003839535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9949579,"threshold_uncertainty_score":0.5208823,"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."}}