{"id":"W4372267664","doi":"10.1109/icassp49357.2023.10097215","title":"Pseudo-Inverted Bottleneck Convolution for Darts Search Space","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Toronto","funders":"","keywords":"Bottleneck; Computer science; Block (permutation group theory); Memory footprint; Architecture; Footprint; Convolutional neural network; Convolution (computer science); Layer (electronics); Network architecture; Code (set theory); Algorithm; Computer engineering; Artificial intelligence; Artificial neural network; Computer network; Embedded system; Mathematics; Set (abstract data type)","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":[0.0004822646,0.0006659835,0.0004006432,0.0003953158,0.0002082817,0.0006555248,0.001084432,0.0006074914,0.00600995],"category_scores_gemma":[0.001576135,0.0002595989,0.0003624486,0.0002805906,0.0004392251,0.001213672,0.0009643009,0.0009376326,0.001114558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008095341,"about_ca_system_score_gemma":0.0008950014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002509968,"about_ca_topic_score_gemma":0.00669397,"domain_scores_codex":[0.9998202,0.00002885755,0.00001042485,0.00003885156,0.0000687978,0.00003304933],"domain_scores_gemma":[0.9997061,0.00008073452,0.00003173529,0.0000777223,0.00007568237,0.00002809975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003693512,0.0001288482,0.002064121,0.0002789755,0.00008995049,0.0002752629,0.0001184375,0.4428961,0.04246281,0.05706386,0.01395297,0.4402993],"study_design_scores_gemma":[0.00001439045,0.00006446376,0.0001533792,0.000009776983,0.000008184579,0.00006145452,0.000009425749,0.982021,0.007076675,0.007623304,0.002952988,0.000004971352],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06018088,0.0006173106,0.9215758,0.0003446398,0.0001346669,0.00008028978,0.0002091744,0.004516626,0.01234062],"genre_scores_gemma":[0.6038021,0.0002752308,0.3847044,0.0003831177,0.00004129656,0.0001904402,0.0005964469,0.0005398947,0.009466979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00600995,"threshold_uncertainty_score":0.02010524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04723404990737102,"score_gpt":0.3106991916403097,"score_spread":0.2634651417329387,"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."}}