{"id":"W6976661708","doi":"10.60692/x846g-r0p96","title":"Supplementing recurrent neural networks with annealing to solve combinatorial optimization problems","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Metaheuristic Optimization Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Waterloo","funders":"","keywords":"Travelling salesman problem; Simulated annealing; Combinatorial optimization; Extremal optimization; Optimization problem; Scheduling (production processes); Recurrent neural network; Cross-entropy method; Artificial neural network","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001118031,0.0002102636,0.0002358184,0.0006396401,0.0003385169,0.001092136,0.0006175085,0.0000734063,0.00001682114],"category_scores_gemma":[0.00005509486,0.0001756365,0.00004467722,0.002151583,0.00001695799,0.001395763,0.0003510067,0.0001507875,0.0002199928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001246092,"about_ca_system_score_gemma":0.00005379838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000056026,"about_ca_topic_score_gemma":1.102632e-7,"domain_scores_codex":[0.9974619,0.00009889688,0.000728901,0.0003087953,0.0008442075,0.0005573414],"domain_scores_gemma":[0.9983987,0.0000246147,0.0003028073,0.0005245897,0.0005288961,0.0002204038],"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":[0.00001174732,0.000001487642,0.00224834,0.00009564693,0.00001751245,0.000003379017,0.01144092,0.9838856,5.177782e-8,0.0009597554,0.0002606316,0.001074949],"study_design_scores_gemma":[0.0008414372,0.0001019706,0.0003975626,0.00009121203,0.000006514464,0.00001314754,0.0009767269,0.9971918,0.00001530364,8.76072e-7,0.0001541463,0.0002092862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002766753,9.363458e-7,0.9934428,0.0002048775,0.001411833,0.0009915687,0.00002142775,0.0007863957,0.0003734053],"genre_scores_gemma":[0.8764499,3.220006e-7,0.1227411,0.0001027106,0.0002019519,0.0002807361,0.0001519458,0.00002287893,0.00004840884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8736832,"threshold_uncertainty_score":0.9999448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0394041072130961,"score_gpt":0.2452516402882114,"score_spread":0.2058475330751153,"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."}}