{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003902639,0.0001251118,0.0002644549,0.0008908973,0.0002266656,0.0001549982,0.0004099233,0.0000324816,0.000004832739],"category_scores_gemma":[0.00008730941,0.0001325689,0.00005502047,0.002073739,0.0000185786,0.002389496,0.0005213618,0.0001977467,0.000001480265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003912278,"about_ca_system_score_gemma":0.0000314244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001344826,"about_ca_topic_score_gemma":0.00001864893,"domain_scores_codex":[0.9984887,0.0002696595,0.000554515,0.0001606252,0.0003234442,0.0002030275],"domain_scores_gemma":[0.999139,0.0001554642,0.0003072428,0.0002546826,0.00008253903,0.00006110242],"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":[0.000006909373,0.00001997923,0.03259747,0.000009658886,0.00004065614,0.000001338343,0.00601106,0.6652304,0.00005667848,0.0002018808,0.00001872184,0.2958052],"study_design_scores_gemma":[0.0002201224,0.00006973618,0.2311338,0.000002684663,0.00002949507,0.000001262178,0.0001024492,0.7677619,0.00004928892,0.00003020025,0.0005077289,0.00009127742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4536285,0.000008053711,0.5459111,0.0001034231,0.00008625421,0.0001210804,0.000009221066,0.0000415595,0.0000908632],"genre_scores_gemma":[0.9850382,0.000002049713,0.0145041,0.0003236472,0.00003828564,0.000006598403,0.00008280874,0.000003317419,0.000001017268],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5314097,"threshold_uncertainty_score":0.5406002,"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."}}