{"id":"W3034408737","doi":"10.48550/arxiv.1911.08019","title":"Online Learned Continual Compression with Adaptive Quantization Modules","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Encoder; Quantization (signal processing); Data compression; USable; Artificial intelligence; Reinforcement learning; Machine learning; Algorithm; Multimedia","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":[0.001466472,0.0007772923,0.001057629,0.0005924567,0.0003222229,0.0007829529,0.002375835,0.001094426,0.001902173],"category_scores_gemma":[0.006143056,0.0003974281,0.0003754035,0.0007752244,0.001244501,0.002579333,0.001911028,0.00182941,0.000556095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007747248,"about_ca_system_score_gemma":0.0009966794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002591921,"about_ca_topic_score_gemma":0.002852428,"domain_scores_codex":[0.9994982,0.0001115668,0.00002987764,0.0001709264,0.0001329552,0.00005633883],"domain_scores_gemma":[0.9980563,0.0009401885,0.0001596173,0.0004824202,0.0002574154,0.0001039526],"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":[0.0003717321,0.0003496957,0.002737018,0.0001645911,0.00008813962,0.0001535076,0.0001614795,0.5657422,0.00747925,0.01364951,0.004787333,0.4043156],"study_design_scores_gemma":[0.00001580979,0.00005128364,0.0001691762,0.000008400431,0.000005870865,0.00003397331,0.000008712196,0.9905698,0.001984308,0.006734496,0.0004107342,0.000007375761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06911877,0.001103535,0.92365,0.0005675408,0.0001030416,0.0001005324,0.0002649903,0.002993432,0.002098135],"genre_scores_gemma":[0.7992065,0.0003080217,0.1955488,0.0004343215,0.000111791,0.0001900152,0.0006326531,0.0001375015,0.003430473],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002591921,"threshold_uncertainty_score":0.007755518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06811625650054115,"score_gpt":0.1896039867010142,"score_spread":0.1214877302004731,"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."}}