{"id":"W3121130100","doi":"10.48550/arxiv.2101.11744","title":"On the mapping between Hopfield networks and Restricted Boltzmann Machines","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; MNIST database; Binary number; Initialization; Restricted Boltzmann machine; Uncorrelated; Gaussian; Computer science; Boltzmann constant; Theoretical computer science; Artificial intelligence; Hopfield network; Statistical physics; Statistical mechanics; Algorithm; Machine learning; Artificial neural network; Pattern recognition (psychology); Mathematics; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002330428,0.0003226777,0.000348328,0.0001347892,0.0003709014,0.0004104129,0.001219376,0.0002694495,0.00002609606],"category_scores_gemma":[0.00010446,0.0002726851,0.0001655749,0.0006237388,0.0001044096,0.0002332022,0.002138554,0.0008081426,0.000006341851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004968758,"about_ca_system_score_gemma":0.00007483596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001983864,"about_ca_topic_score_gemma":0.00003433446,"domain_scores_codex":[0.9980189,0.0003908892,0.000183207,0.0009819911,0.00009117612,0.0003338422],"domain_scores_gemma":[0.9977477,0.0007465503,0.0001950969,0.001070967,0.000115799,0.0001238658],"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":[0.00001542615,0.00004696389,0.00508052,0.0000293451,0.000319235,0.0003495797,0.0002716449,0.9428019,0.00002410829,0.04000444,0.002708343,0.008348511],"study_design_scores_gemma":[0.0001711444,0.00003270058,0.009250883,0.0001309239,0.00005492154,0.000001921743,0.00006734953,0.98076,0.00004008505,0.008787178,0.0003452156,0.0003576232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1351352,0.0002323868,0.8617635,0.0008434578,0.0004501439,0.0002133809,0.000004701999,0.00009562243,0.001261631],"genre_scores_gemma":[0.997091,0.0004629481,0.001252355,0.0003883792,0.0002925959,0.000001121357,0.00001429634,0.00001417852,0.0004831544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8619558,"threshold_uncertainty_score":0.9999725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06333163699085079,"score_gpt":0.1767309694938363,"score_spread":0.1133993325029855,"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."}}