{"id":"W4386065782","doi":"10.1109/cvpr52729.2023.01935","title":"Simulated Annealing in Early Layers Leads to Better Generalization","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Initialization; Computer science; Artificial intelligence; Margin (machine learning); Gradient descent; Benchmark (surveying); Stochastic gradient descent; Machine learning; Transfer of learning; Generalization; Forgetting; Overfitting; Simulated annealing; Matching (statistics); Algorithm; Artificial neural network; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002295625,0.002063509,0.001782465,0.0008972505,0.0008120601,0.001383581,0.001859864,0.001840852,0.004479464],"category_scores_gemma":[0.009320966,0.0009617712,0.001526801,0.0005409786,0.001038248,0.00326911,0.001427287,0.003171483,0.001642877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001313253,"about_ca_system_score_gemma":0.001400939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007341496,"about_ca_topic_score_gemma":0.01069284,"domain_scores_codex":[0.9990638,0.0002523588,0.0000718792,0.0003168913,0.0001590725,0.0001359456],"domain_scores_gemma":[0.9966242,0.001577508,0.0002104634,0.001031226,0.0004546779,0.0001020053],"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":[0.0002144242,0.0001528713,0.002291968,0.0001545613,0.0001297514,0.0001300088,0.0001765515,0.8491498,0.010863,0.00652256,0.004638698,0.1255758],"study_design_scores_gemma":[0.000008596141,0.00003622522,0.0002206238,0.00001039921,0.0000112475,0.00002179758,0.00001050232,0.9914204,0.003395309,0.004199619,0.0006564324,0.00000885407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09083543,0.001036528,0.892646,0.0009201522,0.0002254333,0.0001349905,0.0001743367,0.006658638,0.007368586],"genre_scores_gemma":[0.7139181,0.0004853369,0.2772019,0.0006414031,0.00008780495,0.0002393202,0.0006401562,0.0010796,0.005706371],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007341496,"threshold_uncertainty_score":0.01498532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02811438426582509,"score_gpt":0.2791647282253171,"score_spread":0.251050343959492,"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."}}