{"id":"W4220727198","doi":"10.31219/osf.io/4yz8f","title":"Learning strides in convolutional neural networks","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Upsampling; Computer science; Pooling; Regularization (linguistics); Computational complexity theory; Convolutional neural network; Algorithm; Network architecture; Artificial intelligence; Stochastic gradient descent; Artificial neural network; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006682792,0.000196271,0.0002304947,0.0002412561,0.0001909137,0.0002840572,0.001024209,0.0001240852,0.0009142822],"category_scores_gemma":[0.00009690919,0.0002144549,0.0001076674,0.0003520268,0.00003617087,0.0001903382,0.002435373,0.002098092,0.00001718693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001588126,"about_ca_system_score_gemma":0.0001491865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001333394,"about_ca_topic_score_gemma":0.0000233387,"domain_scores_codex":[0.9979537,0.0003518104,0.000350364,0.0006003545,0.0004024216,0.0003413352],"domain_scores_gemma":[0.9991151,0.0002334688,0.0001774788,0.000347391,0.00004419002,0.00008235237],"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":[0.00000402902,0.0000186971,0.005985318,0.000006764014,0.000007875913,0.00002505258,0.000328948,0.9446201,0.00000185081,0.03416959,0.0002719506,0.01455986],"study_design_scores_gemma":[0.0002101054,0.00003059833,0.01380358,0.00001185473,0.00000170488,0.000006102991,0.0002039182,0.9758634,6.990081e-7,0.001356666,0.008278321,0.000233048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01319815,0.0004240092,0.9645474,0.0009590563,0.00162108,0.0002302962,0.000001158257,0.0004590751,0.0185598],"genre_scores_gemma":[0.9801701,0.00003666229,0.01526745,0.0005317722,0.0001115444,0.0000550421,0.00005692662,0.00001452804,0.003755986],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9669719,"threshold_uncertainty_score":0.999999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02693017571803132,"score_gpt":0.2649890454092965,"score_spread":0.2380588696912652,"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."}}