{"id":"W3125085017","doi":"","title":"Leaky Tiling Activations: A Simple Approach to Learning Sparse Representations Online","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Regularization (linguistics); Simple (philosophy); Artificial neural network; Online algorithm; Artificial intelligence; Algorithm; Deep learning; Function (biology); Pattern recognition (psychology)","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":[0.0008766413,0.0007663793,0.0008156613,0.0003929092,0.0003234362,0.0007026865,0.001568687,0.001185234,0.004043927],"category_scores_gemma":[0.003923325,0.0004475871,0.0004886341,0.0005403341,0.00125955,0.002118357,0.001818416,0.002219791,0.0007619835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004859519,"about_ca_system_score_gemma":0.0006960439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001003627,"about_ca_topic_score_gemma":0.001168589,"domain_scores_codex":[0.9996185,0.0001198153,0.00002093736,0.0001054171,0.00008838147,0.00004686596],"domain_scores_gemma":[0.9992017,0.0003740823,0.00008136919,0.0001858983,0.00008774837,0.00006912585],"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":[0.0002469238,0.0001581948,0.0007365395,0.0001363593,0.00007350417,0.000146431,0.0002087696,0.651787,0.02304838,0.0902773,0.003078519,0.2301021],"study_design_scores_gemma":[0.00000989263,0.00003975867,0.00004369239,0.000005421086,0.000004497077,0.00002479386,0.000006579413,0.9725623,0.00260939,0.02382209,0.0008654499,0.00000611533],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005570038,0.00005821227,0.9930274,0.0001268426,0.00002565272,0.00002399151,0.00002036824,0.0004240944,0.0007234572],"genre_scores_gemma":[0.5107716,0.0002514777,0.4821554,0.0003576334,0.0001105188,0.0002780272,0.0001497315,0.0003119026,0.005613683],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004043927,"threshold_uncertainty_score":0.01352829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1131943599475023,"score_gpt":0.3721155278946628,"score_spread":0.2589211679471605,"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."}}