{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002910916,0.000221771,0.0001863158,0.0002862534,0.0003981368,0.0003247938,0.0006626809,0.0002439749,0.00002484179],"category_scores_gemma":[0.0003661476,0.0002826318,0.00005630949,0.0004658285,0.0001155733,0.002279746,0.001431716,0.0005855265,0.00007809963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000149706,"about_ca_system_score_gemma":0.00007769472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001010647,"about_ca_topic_score_gemma":0.00000638549,"domain_scores_codex":[0.9986242,0.0002208548,0.0002366038,0.0005774566,0.0001243442,0.0002165456],"domain_scores_gemma":[0.9985916,0.000129146,0.0004430756,0.0005224893,0.0002140471,0.0000996563],"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":[0.00001102502,0.00001109058,0.002602922,0.00003749949,0.00002432718,0.000005453367,0.001090085,0.9674179,0.000003698575,0.02251586,0.0002585374,0.006021609],"study_design_scores_gemma":[0.0003304216,0.00004193577,0.0009140384,0.00003617411,0.00003650221,0.000004108237,0.0001573249,0.9852446,0.00002023128,0.01263825,0.0003075822,0.0002688589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05531458,0.00001570134,0.9421192,0.0001216464,0.000342322,0.0002259192,0.000003785923,0.0003349641,0.001521816],"genre_scores_gemma":[0.9708219,0.00006463908,0.0284138,0.00004796096,0.0000512706,0.000001456453,0.000218902,0.00001196204,0.0003681684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9155073,"threshold_uncertainty_score":0.9999626,"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."}}