{"id":"W2798769807","doi":"10.48550/arxiv.1805.01317","title":"SdcNet: A Computation-Efficient CNN for Object Recognition","year":2018,"lang":"en","type":"preprint","venue":"Spectrum Research Repository (Concordia University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"FLOPS; Computation; Computer science; Convolution (computer science); Convolutional neural network; Word error rate; Feature (linguistics); Cognitive neuroscience of visual object recognition; Object (grammar); Task (project management); Artificial intelligence; Pattern recognition (psychology); Volume (thermodynamics); Hyperparameter; Algorithm; Artificial neural network; Parallel computing","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":[0.0003688096,0.0009960904,0.0004893351,0.0007597263,0.0002989754,0.0006379754,0.002112619,0.0006402206,0.003687948],"category_scores_gemma":[0.0009989657,0.0004561737,0.0004812938,0.001021542,0.0003643071,0.001362188,0.00103586,0.001007805,0.001413627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006993791,"about_ca_system_score_gemma":0.001104893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007520444,"about_ca_topic_score_gemma":0.01067966,"domain_scores_codex":[0.9997517,0.00001958904,0.00001437411,0.00007378979,0.00009859409,0.00004184886],"domain_scores_gemma":[0.9998072,0.00003048791,0.00001890731,0.00005256708,0.00007233056,0.00001847352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004612816,0.0002147776,0.002008083,0.0003856099,0.0002448579,0.0002655153,0.00005456093,0.1368914,0.07130631,0.01331283,0.03950086,0.7353539],"study_design_scores_gemma":[0.0000283231,0.00008794414,0.0007507058,0.00001796241,0.00002718102,0.0001491962,0.00000915412,0.9451332,0.03801334,0.003897304,0.01186556,0.00002012393],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03233215,0.0009129961,0.9465728,0.0002270965,0.0003171554,0.0001875036,0.001537112,0.01183759,0.006075555],"genre_scores_gemma":[0.3322358,0.001027128,0.6418909,0.0004074895,0.00009447221,0.0003700409,0.008512638,0.0006982405,0.01476338],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007520444,"threshold_uncertainty_score":0.01495332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06196747260812523,"score_gpt":0.3151904038340808,"score_spread":0.2532229312259556,"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."}}