{"id":"W2963324979","doi":"10.1109/icdsp.2018.8631567","title":"SdcNet: A Computation-Efficient CNN for Object Recognition","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"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; Cognitive neuroscience of visual object recognition; Feature (linguistics); Object (grammar); Task (project management); Artificial intelligence; Pattern recognition (psychology); Volume (thermodynamics); Artificial neural network; Algorithm; 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":[0.0003838256,0.0009586635,0.000499716,0.0007325414,0.0002929201,0.0005787682,0.002066557,0.000620721,0.003353697],"category_scores_gemma":[0.000914172,0.0004365715,0.0004635699,0.001012003,0.0003553178,0.001321202,0.0009706204,0.0009943845,0.001198991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006975154,"about_ca_system_score_gemma":0.001107024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008293156,"about_ca_topic_score_gemma":0.0116918,"domain_scores_codex":[0.9997588,0.00001899599,0.00001371827,0.00006835632,0.0000982968,0.00004183036],"domain_scores_gemma":[0.9998173,0.00002886737,0.00001882045,0.00004505983,0.00007180202,0.00001822741],"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":[0.0004302524,0.000192012,0.001897439,0.0003820751,0.0002399818,0.0002532472,0.00004816537,0.1418337,0.07105524,0.01216502,0.03449772,0.7370052],"study_design_scores_gemma":[0.00002652805,0.00008561949,0.0006987566,0.00001738596,0.00002595298,0.0001451725,0.000008154825,0.9508648,0.03437863,0.003118664,0.01060955,0.00002083452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02961758,0.001028668,0.9518935,0.0002176739,0.0003057117,0.0001751373,0.001212702,0.01005759,0.005491464],"genre_scores_gemma":[0.3426838,0.001198839,0.6339434,0.0004513091,0.00009538377,0.0003550258,0.006786266,0.0005885866,0.01389725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008293156,"threshold_uncertainty_score":0.01648974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04071669672122831,"score_gpt":0.3065425189119911,"score_spread":0.2658258221907628,"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."}}