{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003948837,0.0002911522,0.0002771117,0.0005659813,0.0007878482,0.001003982,0.0009841816,0.0001068339,0.0006951997],"category_scores_gemma":[0.003470939,0.0003359381,0.0001727961,0.001316233,0.00005897957,0.0009870438,0.0004443726,0.001017431,0.0004869577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001589648,"about_ca_system_score_gemma":0.0003652719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000102943,"about_ca_topic_score_gemma":0.00003200745,"domain_scores_codex":[0.9963187,0.0005003831,0.000629587,0.001123675,0.0009858138,0.0004418465],"domain_scores_gemma":[0.9969359,0.0006020276,0.0003174295,0.000668745,0.001194461,0.0002814213],"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":[0.00005828708,0.0008185004,0.00783655,0.00001464452,0.000203326,0.00006530481,0.01017289,0.5089427,0.01317875,0.4278668,0.002270381,0.02857189],"study_design_scores_gemma":[0.001122044,0.0001387094,0.03319839,0.00009839188,0.00002608002,0.00008873638,0.01485503,0.8721021,0.001626669,0.005742495,0.07029265,0.0007086401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03745668,0.0000248045,0.7700796,0.007973978,0.0005330917,0.0003568428,0.00001678851,0.0006776455,0.1828805],"genre_scores_gemma":[0.9144657,0.00005183145,0.05996735,0.0008728828,0.000224586,0.0001333672,0.0008104286,0.00003773319,0.0234361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.877009,"threshold_uncertainty_score":0.9999093,"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."}}