{"id":"W4379523021","doi":"10.21428/594757db.05a13011","title":"PCA-Enhanced Autoencoders for Nonlinear Dimensionality Reduction in Low Data Regimes","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Dimensionality reduction; Principal component analysis; Reduction (mathematics); Computer science; Curse of dimensionality; Nonlinear system; Pattern recognition (psychology); Artificial intelligence; Data mining; Data reduction; Dimensional reduction; Machine learning; Mathematics; Physics","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":[0.0009626797,0.0008975964,0.0005920595,0.0006394872,0.0003107959,0.0005629124,0.0005455496,0.0006361667,0.001572811],"category_scores_gemma":[0.003255029,0.0003239577,0.0006409578,0.000911161,0.0006025921,0.001095042,0.0007596506,0.001600396,0.0008793008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003239833,"about_ca_system_score_gemma":0.0007020661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00221703,"about_ca_topic_score_gemma":0.00332028,"domain_scores_codex":[0.9994811,0.0001286195,0.00004408216,0.0001041425,0.0002020294,0.00003994823],"domain_scores_gemma":[0.998804,0.0006258717,0.00007745498,0.0002008244,0.000267296,0.00002455282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000200214,0.0001595142,0.001434516,0.0002300785,0.0001731368,0.0001879189,0.0001782407,0.333566,0.05131114,0.02501388,0.006838006,0.5807073],"study_design_scores_gemma":[0.000006441206,0.00003566114,0.0006525119,0.00001599492,0.00001583348,0.00006284173,0.00001431876,0.9786052,0.01196789,0.005745459,0.002863057,0.00001493788],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01444527,0.0006978419,0.9824421,0.000225885,0.00006942295,0.00003097833,0.0001014725,0.0006260078,0.001360966],"genre_scores_gemma":[0.3073693,0.001896795,0.6826942,0.0002573273,0.0001759326,0.0001892822,0.0009041567,0.0001979188,0.006315165],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00221703,"threshold_uncertainty_score":0.0052616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06154594188134382,"score_gpt":0.353097162862792,"score_spread":0.2915512209814481,"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."}}