{"id":"W2057913154","doi":"10.1109/nafips.2010.5548182","title":"Hopfield neural networks as pseudo random number generators","year":2010,"lang":"en","type":"article","venue":"","topic":"Chaos-based Image/Signal Encryption","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Pseudorandom number generator; NIST; Computer science; Random number generation; Artificial neural network; Hopfield network; Random seed; Cryptography; Generator (circuit theory); Key (lock); Task (project management); Artificial intelligence; Algorithm; Engineering; Speech recognition; Computer security","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002882095,0.0001652157,0.0001524257,0.00004846436,0.0001364908,0.0002767264,0.0006611767,0.0001204698,0.001074293],"category_scores_gemma":[0.00006079633,0.0001384557,0.0001039153,0.0003129741,0.00004721358,0.0006212441,0.0001782385,0.0004277375,0.000470208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001316726,"about_ca_system_score_gemma":0.00004380707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001764461,"about_ca_topic_score_gemma":0.00007288778,"domain_scores_codex":[0.9987515,0.00005870394,0.0002118236,0.0003836933,0.0002611086,0.0003332028],"domain_scores_gemma":[0.9989517,0.0001481706,0.00006001936,0.000588174,0.00008310576,0.000168848],"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":[0.0002856755,0.0004559597,0.01054776,0.00002611113,0.000106812,0.000381405,0.0007908018,0.02389242,0.1443542,0.2831094,0.1571076,0.3789419],"study_design_scores_gemma":[0.001177627,0.00004007414,0.0003189317,0.000002662529,0.000005784569,0.0001082011,0.000005118039,0.9820325,0.01206692,0.001919999,0.002062015,0.0002601767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2125165,0.00001179058,0.7713721,0.001460586,0.002012755,0.0001454219,2.86133e-7,0.0003456336,0.01213497],"genre_scores_gemma":[0.9571939,0.000004158923,0.03783213,0.003473614,0.0005550763,0.00001469701,0.000002538811,0.00001320783,0.0009106905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9581401,"threshold_uncertainty_score":0.9998389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006050190101046442,"score_gpt":0.2324748244437102,"score_spread":0.2264246343426638,"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."}}