{"id":"W4382468866","doi":"10.1609/aaai.v37i7.26061","title":"Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization for Heterogeneous Representational Coarseness","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Discretization; Vector quantization; Codebook; Computer science; Bottleneck; Reinforcement learning; Quantization (signal processing); Hyperparameter; Artificial intelligence; Learning vector quantization; Robustness (evolution); Generalization; Theoretical computer science; Machine learning; Algorithm; 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":[0.003511373,0.0008725637,0.001503606,0.0006097604,0.0006406719,0.001740048,0.002256306,0.001157163,0.001887847],"category_scores_gemma":[0.02110744,0.000589165,0.0004766388,0.0008422052,0.001686551,0.005067222,0.003329676,0.003121956,0.0003501814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001931427,"about_ca_system_score_gemma":0.001796923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004572927,"about_ca_topic_score_gemma":0.003791384,"domain_scores_codex":[0.998351,0.0005129505,0.0001460429,0.0003755824,0.0004131519,0.0002014245],"domain_scores_gemma":[0.9920773,0.004890634,0.0008304405,0.001196661,0.0006800208,0.0003249615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002330109,0.0001610653,0.001551586,0.00008861276,0.00003554722,0.00009409786,0.0002884675,0.8874987,0.004957766,0.03902453,0.001822161,0.06424443],"study_design_scores_gemma":[0.00001200197,0.00002043015,0.00007199014,0.000004854936,0.000002861041,0.000007823788,0.00001305725,0.9861683,0.0006099548,0.01290861,0.0001744533,0.000005778073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05335047,0.0004276549,0.9437913,0.0004690487,0.0000595938,0.00006539545,0.00007615667,0.0006204465,0.001139888],"genre_scores_gemma":[0.9193399,0.0001774313,0.07866446,0.0002069876,0.00004843568,0.0001590098,0.0001414385,0.00009670702,0.001165616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004572927,"threshold_uncertainty_score":0.01857013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07642449509526475,"score_gpt":0.3147651972544703,"score_spread":0.2383407021592055,"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."}}