{"id":"W2153346333","doi":"10.1609/aaai.v28i1.8924","title":"On the Challenges of Physical Implementations of RBMs","year":2014,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Implementation; Markov chain Monte Carlo; Physical system; Boltzmann machine; Computation; Software; Sampling (signal processing); Inference; Computer engineering; Focus (optics); Variety (cybernetics); Stochastic computing; Range (aeronautics); Theoretical computer science; Distributed computing; Machine learning; Computational science; Artificial intelligence; Deep learning; Algorithm; Software engineering; Bayesian probability","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":[],"consensus_categories":[],"category_scores_codex":[0.0005076508,0.0001356795,0.0002298438,0.00005760159,0.0001150825,0.0000438901,0.001362035,0.00003065331,0.00002961244],"category_scores_gemma":[0.0004942942,0.00007823442,0.0001289577,0.000298808,0.0002865085,0.0001553884,0.0002111683,0.0001287425,0.00001282724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009553716,"about_ca_system_score_gemma":0.00003343612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002699833,"about_ca_topic_score_gemma":0.000009182228,"domain_scores_codex":[0.9987975,0.00004322447,0.0003590188,0.0002555108,0.0003690287,0.0001757572],"domain_scores_gemma":[0.998315,0.0004740096,0.0004029691,0.000295102,0.0004801484,0.00003272574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001396458,0.0001154413,0.00001332768,0.00001404825,0.00001394693,1.205394e-8,0.001544556,0.0002690906,0.04173192,0.9074436,0.00007313907,0.04876694],"study_design_scores_gemma":[0.00001358195,0.0002901874,0.0001610405,0.00008857259,0.000008438597,1.694237e-7,0.000522389,0.09033486,0.6349689,0.2735206,0.00002445086,0.0000668209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5604473,0.00007486148,0.3223644,0.03812897,0.0008746421,0.001464173,0.00002537104,0.00008830362,0.07653201],"genre_scores_gemma":[0.9986926,0.00002365778,0.001088705,0.00009112404,0.00006276034,0.0000143583,9.539351e-8,0.000005440093,0.00002122371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.633923,"threshold_uncertainty_score":0.3190307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08616196602842285,"score_gpt":0.3009716672235438,"score_spread":0.214809701195121,"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."}}