{"id":"W4386634632","doi":"10.1109/tpami.2023.3302150","title":"Information Bottleneck and Aggregated Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Key Research and Development Program of China; Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Information bottleneck method; Learning vector quantization; Artificial intelligence; Computer science; Competitive learning; Artificial neural network; Machine learning; Instance-based learning; Vector quantization; Feature learning; Semi-supervised learning; Quantization (signal processing); Contextual image classification; Pattern recognition (psychology); Image (mathematics); Algorithm; Mutual information","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":[0.0003055807,0.0001406325,0.000178655,0.0007618462,0.0003026902,0.0002665077,0.0001822878,0.00004899735,0.00006808064],"category_scores_gemma":[0.00001275829,0.0001296612,0.00009114303,0.001710693,0.00004184729,0.000578198,0.000007066673,0.0002570412,0.000146154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001386413,"about_ca_system_score_gemma":0.00001083484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002807078,"about_ca_topic_score_gemma":0.0001167095,"domain_scores_codex":[0.9990003,0.00008085781,0.000278648,0.0002289746,0.0002202675,0.0001909968],"domain_scores_gemma":[0.999406,0.0001307085,0.00009949734,0.0001979627,0.00005633876,0.0001094676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003995272,0.00001302748,0.0006813324,0.000009551072,0.0001231451,0.000003014644,0.001380234,0.07598722,0.00007094468,0.0001166791,0.000006625556,0.9216042],"study_design_scores_gemma":[0.0001044192,0.00008045325,0.004832562,0.00001710437,0.00009685097,0.000008016557,0.0003366316,0.9863352,0.006684881,0.0001394147,0.001165993,0.0001984342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01140465,0.00003836882,0.9874899,0.0004758367,0.0000996629,0.00006487778,0.000005055574,0.0002547479,0.0001669056],"genre_scores_gemma":[0.9978485,0.00067098,0.0007120629,0.0003373708,0.000006222534,0.00001087693,0.00001115907,0.000005548184,0.000397246],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9867778,"threshold_uncertainty_score":0.5287433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01830419734807983,"score_gpt":0.2581165396701066,"score_spread":0.2398123423220267,"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."}}