{"id":"W3156106686","doi":"10.1016/j.asoc.2021.107424","title":"Learning to extract robust handcrafted features with a single observation via evolutionary neurogenesis","year":2021,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Neurogenesis; Artificial intelligence; Robustness (evolution); Convolutional neural network; Machine learning; Evolutionary algorithm; Particle swarm optimization; Deep learning; Artificial neural network; Pattern recognition (psychology); Neuroscience","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":[0.00007252937,0.0001744884,0.0001672688,0.00007269828,0.0002145353,0.00008376285,0.00007173215,0.00007575759,0.000008996542],"category_scores_gemma":[0.00003525335,0.0001891957,0.00003285963,0.0005446108,0.00001194225,0.00005222559,0.00003558587,0.000179764,0.000014564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007900011,"about_ca_system_score_gemma":0.00002444569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006698921,"about_ca_topic_score_gemma":0.00001291049,"domain_scores_codex":[0.9990237,0.00002618805,0.0002032377,0.0002751029,0.0002028496,0.0002688868],"domain_scores_gemma":[0.9994893,0.000114668,0.00004109864,0.0001561278,0.0001133136,0.00008546902],"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":[0.00001137924,0.00002556812,0.001054717,0.00003316124,0.00002135193,0.00001656776,0.000219814,0.9104266,0.07589084,0.00009750846,0.0001769655,0.01202556],"study_design_scores_gemma":[0.0002847756,0.00004492508,0.01047072,0.00005491222,0.00002498174,0.00002911404,0.0001577081,0.9720353,0.01562351,0.00002795362,0.000953557,0.0002925326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3856043,0.00009018448,0.6132568,0.00006064262,0.0001111209,0.0001118392,6.312202e-7,0.000371399,0.0003931028],"genre_scores_gemma":[0.9335859,0.000002729036,0.0658922,0.000194067,0.000110562,0.000005528461,0.00008642545,0.00005906105,0.00006346431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5479817,"threshold_uncertainty_score":0.7715178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01238834181118295,"score_gpt":0.1841450278322308,"score_spread":0.1717566860210478,"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."}}