{"id":"W4375869437","doi":"10.1109/icassp49357.2023.10094582","title":"Performing Neural Architecture Search Without Gradients","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial neural network; Architecture; Kernel (algebra); Ranking (information retrieval); Process (computing); Artificial intelligence; Code (set theory); Beam search; Margin (machine learning); Machine learning; Gaussian process; Search algorithm; Gaussian; Algorithm; Mathematics","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":[0.00009927924,0.00009442435,0.00008001283,0.0001140032,0.0002169785,0.00006123326,0.0007426688,0.00002370587,0.0000103571],"category_scores_gemma":[0.00001011624,0.00007672596,0.00003700123,0.001152434,0.00002634659,0.0002353728,0.0003912651,0.000178585,0.0003805197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001654264,"about_ca_system_score_gemma":0.00001344668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005592492,"about_ca_topic_score_gemma":0.000007109873,"domain_scores_codex":[0.9989259,0.00002353885,0.0001090297,0.0003351309,0.0002279357,0.000378458],"domain_scores_gemma":[0.999276,0.00007607733,0.00001943002,0.0004954896,0.00002912186,0.0001038718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008542935,0.00004803084,0.01369743,0.00002164488,0.00001691099,0.00003681873,0.001638597,0.08029152,0.006009465,0.1572986,0.003931645,0.7370008],"study_design_scores_gemma":[0.0001762501,0.00004063222,0.01045458,0.000005809402,0.000001554076,0.00003935354,0.00002573437,0.9724243,0.001980166,0.008978096,0.005678965,0.0001945845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3392451,0.00001320254,0.651264,0.003886875,0.0001865928,0.0002689223,9.360195e-7,0.001345051,0.003789373],"genre_scores_gemma":[0.9586571,0.000007223015,0.03822564,0.0003598587,0.00007744579,0.00003391078,0.000003904068,0.00001088671,0.002624053],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8921328,"threshold_uncertainty_score":0.4890938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03050067906354909,"score_gpt":0.298351156787732,"score_spread":0.2678504777241829,"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."}}