{"id":"W1853900790","doi":"10.48550/arxiv.1312.5663","title":"k-Sparse Autoencoders","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":148,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Autoencoder; MNIST database; Dropout (neural networks); Pattern recognition (psychology); Neural coding; Computer science; Artificial intelligence; Encoding (memory); Noise reduction; Sparse approximation; Machine learning; Algorithm; Deep learning","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002135961,0.0002888322,0.0002683244,0.000267871,0.0001757467,0.0002745168,0.001966777,0.0002570975,0.0002261503],"category_scores_gemma":[0.00004059333,0.0003398793,0.0001960728,0.0004621029,0.0001043891,0.0005376056,0.001636196,0.0006823782,0.001319642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001559518,"about_ca_system_score_gemma":0.0002102413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001615577,"about_ca_topic_score_gemma":0.0000142614,"domain_scores_codex":[0.9981322,0.000159532,0.0001852859,0.001016853,0.0001159027,0.0003902393],"domain_scores_gemma":[0.9981208,0.00008691914,0.0002433382,0.001166457,0.0001412988,0.0002411728],"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":[0.00000555659,0.00004963036,0.0005830895,0.00003042476,0.00005724472,0.0001809702,0.0006027476,0.543058,0.00001407235,0.4508218,0.002397119,0.002199405],"study_design_scores_gemma":[0.0003025646,0.0000223802,0.001104497,0.00004125174,0.00001988311,0.000003540091,0.0001249355,0.9475234,0.0000123271,0.04140436,0.00903115,0.0004096924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03571076,0.00004400078,0.9382771,0.0002452457,0.0008480107,0.0002327312,0.000002476421,0.0005526143,0.0240871],"genre_scores_gemma":[0.9738275,0.00009072251,0.01430879,0.0003594423,0.00005833001,0.000001333904,0.000009874821,0.00001867615,0.01132532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9381167,"threshold_uncertainty_score":0.9999053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09595176305524669,"score_gpt":0.1851467634226563,"score_spread":0.08919500036740957,"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."}}