{"id":"W7132944625","doi":"","title":"Comparative Study of Data Efficiency in Vision Transformer and ResNet-18 Architectures: Using CIFAR-10 and TinyImageNet","year":2024,"lang":"en","type":"dissertation","venue":"Trepo - Institutional Repository of Tampere University","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Transformer; RGB color model; Deep learning; Feature extraction; Machine vision; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001194702,0.0002037597,0.000359671,0.0003393856,0.0003059196,0.00002876775,0.0006536947,0.0001026173,0.000003501908],"category_scores_gemma":[0.00001222823,0.0002083082,0.00003685051,0.0005044583,0.0002712892,0.0003941599,0.0002217265,0.0002616286,5.036898e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008683527,"about_ca_system_score_gemma":0.0003028673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003290502,"about_ca_topic_score_gemma":0.0006630791,"domain_scores_codex":[0.9983521,0.00009150655,0.0003562056,0.0007318197,0.0003400926,0.0001282806],"domain_scores_gemma":[0.9988994,0.0001283864,0.0002452109,0.0005374078,0.0001273402,0.00006226868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007014135,0.0130839,0.0103762,0.00645267,0.001979632,0.003509485,0.1911589,0.2997232,0.3579518,0.04226303,0.001541244,0.06494566],"study_design_scores_gemma":[0.01070561,0.004118263,0.2223404,0.005756797,0.001794148,0.001369669,0.03860491,0.6627376,0.0284586,0.003646954,0.01624652,0.004220567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907435,0.0006008337,0.005031667,0.00001048431,0.0001303859,0.0004982185,0.00004739732,0.00002809596,0.002909405],"genre_scores_gemma":[0.9939632,0.00003550501,0.005367595,0.000002032599,0.00001920151,0.000001112596,0.00009850252,0.000005781268,0.0005070004],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3630144,"threshold_uncertainty_score":0.8494562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04936039154501471,"score_gpt":0.3284373596883963,"score_spread":0.2790769681433816,"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."}}