{"id":"W2950100795","doi":"10.1016/j.neunet.2019.06.005","title":"Combining Hopfield neural networks, with applications to grid-based mathematics puzzles","year":2019,"lang":"en","type":"article","venue":"Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hopfield network; Artificial neural network; Computer science; Constraint (computer-aided design); Simple (philosophy); Set (abstract data type); Grid; Solver; Selection (genetic algorithm); Mathematical optimization; Artificial intelligence; Theoretical computer science; Algorithm; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001751493,0.0003919809,0.0004006838,0.0001040833,0.0003350721,0.0004179833,0.001506141,0.0001493851,0.0000315559],"category_scores_gemma":[0.000005496373,0.0003223797,0.0001301591,0.001257628,0.00006193711,0.0003516026,0.0003172461,0.000568036,0.00006678157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003304289,"about_ca_system_score_gemma":0.00002701647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001586767,"about_ca_topic_score_gemma":0.00003702534,"domain_scores_codex":[0.9975085,0.00005936026,0.0004562771,0.0008081773,0.0003757131,0.0007920338],"domain_scores_gemma":[0.9974399,0.0004478739,0.0002161621,0.001432098,0.0001163421,0.0003476709],"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":[0.0000135555,0.00009439338,0.001206756,0.00001428463,0.00001335581,0.000006310023,0.000033985,0.9627822,0.00003944744,0.01303695,0.003385578,0.01937315],"study_design_scores_gemma":[0.0004141761,0.0002000042,0.0004978716,0.00004207854,0.00001699095,0.00002618161,0.00001695822,0.9925699,0.00004035506,0.0002454995,0.00550637,0.0004235803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01935433,0.0001720335,0.9722034,0.004701369,0.0005436862,0.001568227,0.000003774569,0.0005610859,0.0008921082],"genre_scores_gemma":[0.9604645,0.00001202533,0.03266171,0.005411972,0.0006266674,0.0004829016,0.00003223944,0.00005349416,0.0002544536],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9411102,"threshold_uncertainty_score":0.9999228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01403382173678859,"score_gpt":0.2384234187074004,"score_spread":0.2243895969706118,"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."}}