{"id":"W3119446159","doi":"10.48550/arxiv.2101.00793","title":"A Framework for Fast Scalable BNN Inference using Googlenet and Transfer Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"MNIST database; Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Object detection; Transfer of learning; Inference; Scalability; Machine learning; Segmentation; Object (grammar); Contextual image classification; Artificial neural network; Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Computer vision; Image (mathematics); Database","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001368355,0.001892259,0.00151882,0.001581156,0.0007387819,0.001604666,0.004991403,0.001695889,0.01308112],"category_scores_gemma":[0.003144429,0.001384375,0.001566661,0.001438042,0.0007309476,0.003198419,0.002086703,0.002729718,0.006192905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001811058,"about_ca_system_score_gemma":0.002026502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0485818,"about_ca_topic_score_gemma":0.06250583,"domain_scores_codex":[0.9994718,0.00007253601,0.00002978115,0.000161918,0.0001780161,0.00008595343],"domain_scores_gemma":[0.9994512,0.000139322,0.00004065962,0.0001288935,0.0001880071,0.00005198154],"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":[0.0003978427,0.0002231444,0.001167415,0.0002852873,0.0003043165,0.0002321134,0.00007841321,0.4695244,0.003455563,0.02975721,0.04230997,0.4522643],"study_design_scores_gemma":[0.00001906635,0.00001520115,0.0000686757,0.00001306018,0.00001035231,0.00002611371,0.00000800239,0.9864032,0.0006977725,0.009923341,0.002805146,0.00001000781],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004373103,0.000722636,0.9668082,0.0002430108,0.0002771477,0.0001219084,0.0007752727,0.02366326,0.003015473],"genre_scores_gemma":[0.1861313,0.0009382411,0.7925804,0.0005704744,0.0002669763,0.0005948826,0.006701512,0.002413196,0.009803039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0485818,"threshold_uncertainty_score":0.09659809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1054428258629053,"score_gpt":0.2386242129336166,"score_spread":0.1331813870707113,"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."}}