{"id":"W4290058690","doi":"10.1016/j.neucom.2022.08.014","title":"Information flow in Deep Restricted Boltzmann Machines: An analysis of mutual information between inputs and outputs","year":2022,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"H2020 Marie Skłodowska-Curie Actions; Universidad de Buenos Aires; Secretaría de Ciencia y Técnica, Universidad de Buenos Aires; Horizon 2020 Framework Programme; Horizon 2020; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Mutual information; Boltzmann machine; Information flow; Computer science; Flow (mathematics); Artificial intelligence; Restricted Boltzmann machine; Mathematics; Deep learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004599813,0.0008723505,0.00131836,0.001198014,0.0004870484,0.001444153,0.001914145,0.001956167,0.002502861],"category_scores_gemma":[0.01754844,0.001166857,0.0009750303,0.0008358876,0.002363056,0.004100784,0.00220516,0.002433479,0.000265336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001742388,"about_ca_system_score_gemma":0.001090594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0018632,"about_ca_topic_score_gemma":0.001369011,"domain_scores_codex":[0.9988284,0.0005679178,0.00004689009,0.0001886905,0.0002320507,0.0001361035],"domain_scores_gemma":[0.9868075,0.011326,0.0006966075,0.0003729911,0.0005319095,0.0002648804],"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":[0.0001525631,0.00005811167,0.0007650125,0.0001063451,0.00005222103,0.00006562897,0.0001130599,0.8216621,0.001658644,0.1608615,0.001013088,0.01349171],"study_design_scores_gemma":[0.00000439838,0.0000122788,0.0001501937,0.00001068455,0.000006759183,0.00001366683,0.000004419493,0.9550272,0.0003089039,0.04434005,0.0001136877,0.000007710651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06095728,0.0009722568,0.9332532,0.001024428,0.00005979738,0.00004231253,0.0001639958,0.0002961841,0.003230574],"genre_scores_gemma":[0.9499865,0.0007982026,0.04318105,0.000279258,0.0001539379,0.0001445322,0.0002288143,0.0002927601,0.004934907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004599813,"threshold_uncertainty_score":0.02432638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00953680857249059,"score_gpt":0.2239215157268561,"score_spread":0.2143847071543655,"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."}}