{"id":"W2806863256","doi":"10.1609/aaai.v32i1.12155","title":"Training Autoencoders in Sparse Domain","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Discrete cosine transform; Artificial intelligence; Computer science; Sparse approximation; Fast Fourier transform; Encoding (memory); Pattern recognition (psychology); Domain (mathematical analysis); Frequency domain; Dimensionality reduction; Feature (linguistics); Representation (politics); Autoencoder; Discrete Fourier transform (general); Fourier transform; Algorithm; Image (mathematics); Computer vision; Deep learning; Mathematics; Short-time Fourier transform; Fourier analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.0007057014,0.0001985325,0.0002532116,0.0001488294,0.0001836609,0.0002026754,0.001720761,0.00007621268,0.00008324029],"category_scores_gemma":[0.0002957424,0.0001497736,0.00009312413,0.0008640681,0.0004625154,0.0004749772,0.0002969672,0.0002278847,0.0001040998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004346349,"about_ca_system_score_gemma":0.0001111051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005782591,"about_ca_topic_score_gemma":0.00008160253,"domain_scores_codex":[0.9982458,0.00003138918,0.0004712938,0.0004832129,0.0003559202,0.0004123402],"domain_scores_gemma":[0.9989521,0.00007523048,0.000246683,0.0002693496,0.0003805871,0.00007607193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005085744,0.0001100897,0.000196303,0.00001013232,0.00001289767,0.000001096953,0.009266371,0.0004186563,0.03862149,0.8068381,0.0002490291,0.144225],"study_design_scores_gemma":[0.00004619395,0.0002810648,0.0004035578,0.0002463909,0.000005801676,0.000004003286,0.002235122,0.3514365,0.3322682,0.3122236,0.0005397728,0.0003098944],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1708442,0.0000279314,0.7227837,0.00990305,0.001672303,0.000757624,0.000004969006,0.0001577792,0.09384845],"genre_scores_gemma":[0.9716377,0.00001017584,0.02775719,0.0002981427,0.0001548423,0.00001429901,1.226125e-7,0.000008997074,0.0001185272],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8007935,"threshold_uncertainty_score":0.610759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1123061887485974,"score_gpt":0.2962036159536301,"score_spread":0.1838974272050327,"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."}}