{"id":"W3160916081","doi":"","title":"LeanResNet: A Low-cost yet Effective Convolutional Residual Networks","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convolutional neural network; Convolution (computer science); Residual; Computer science; Computational complexity theory; Range (aeronautics); Convolutional code; Pattern recognition (psychology); Artificial intelligence; Filter (signal processing); Algorithm; Artificial neural network; Computer vision; Decoding methods","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005749612,0.001316018,0.0007031816,0.0006767561,0.0002457436,0.0005782532,0.001940162,0.0007159536,0.004123387],"category_scores_gemma":[0.001198821,0.0003954645,0.0005562519,0.0004779513,0.0003914444,0.0014971,0.0009557087,0.0009355057,0.00181376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000507865,"about_ca_system_score_gemma":0.001087996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004459848,"about_ca_topic_score_gemma":0.01043541,"domain_scores_codex":[0.9997047,0.00004459492,0.00001799948,0.00006194958,0.0001172555,0.00005352252],"domain_scores_gemma":[0.9997221,0.00007600523,0.00003897462,0.00005048392,0.00008809668,0.00002439093],"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":[0.0005216149,0.0003202607,0.001498888,0.0004767299,0.0002364689,0.0003909661,0.00007177384,0.3528305,0.04207176,0.02231592,0.02788262,0.5513825],"study_design_scores_gemma":[0.00004163579,0.0001722505,0.0003125395,0.00002705913,0.00003568887,0.0001155684,0.00001530834,0.9720366,0.01412228,0.004353522,0.008744929,0.00002263395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04488745,0.001473305,0.932,0.0002914493,0.0002432333,0.000151659,0.0007058232,0.0133602,0.006886862],"genre_scores_gemma":[0.3644328,0.001097069,0.6101058,0.0004702445,0.0001318401,0.000331165,0.004492506,0.001089623,0.01784902],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004459848,"threshold_uncertainty_score":0.01379412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01699334081363223,"score_gpt":0.2915429403978839,"score_spread":0.2745495995842516,"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."}}