{"id":"W2951873722","doi":"","title":"Learning deep representations by mutual information estimation and maximization","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":514,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Infomax; Artificial intelligence; Mutual information; Computer science; Unsupervised learning; Locality; Representation (politics); Machine learning; Feature learning; Matching (statistics); Maximization; Artificial neural network; Deep learning; Autoencoder; Pattern recognition (psychology); Mathematics","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":[0.003424665,0.001635787,0.001276128,0.0008887232,0.0004804596,0.001497873,0.002089727,0.001708066,0.001768197],"category_scores_gemma":[0.01080026,0.0008035486,0.0009151546,0.0008778258,0.002500742,0.003439333,0.003356191,0.002924139,0.0007477746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001576521,"about_ca_system_score_gemma":0.001362772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001169165,"about_ca_topic_score_gemma":0.001418681,"domain_scores_codex":[0.9983045,0.0008109275,0.00007632128,0.0003617293,0.0003246407,0.0001218765],"domain_scores_gemma":[0.9960185,0.002507512,0.0005171882,0.0005667158,0.0002760621,0.0001140095],"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":[0.0001212749,0.00008604168,0.0007184874,0.0001465085,0.0001206589,0.00005768869,0.00009073845,0.8244452,0.004414351,0.08131944,0.00297894,0.08550062],"study_design_scores_gemma":[0.000005523752,0.00002492058,0.00006725837,0.00001151364,0.000007037248,0.00001415445,0.000005252947,0.9590052,0.001661783,0.03877568,0.0004132724,0.000008466964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006761124,0.0001466905,0.9913608,0.0002575588,0.00001513865,0.00002801781,0.00005318246,0.0003527637,0.001024658],"genre_scores_gemma":[0.6374412,0.0004898856,0.3554456,0.0005271453,0.000145574,0.0003116903,0.0005181023,0.0004684558,0.004652265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003424665,"threshold_uncertainty_score":0.01811153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02527924104425566,"score_gpt":0.1959921560152496,"score_spread":0.1707129149709939,"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."}}