{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001040704,0.0002714217,0.0003096726,0.0001134965,0.000334713,0.0002085512,0.000853873,0.0002807101,0.000009747403],"category_scores_gemma":[0.00005671738,0.0003418287,0.000121492,0.0006157815,0.000103856,0.0004110867,0.001081765,0.0007440179,0.00000379261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001014454,"about_ca_system_score_gemma":0.00015137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003031647,"about_ca_topic_score_gemma":0.00001943485,"domain_scores_codex":[0.9981413,0.00008325168,0.0001687407,0.001172267,0.00006475511,0.0003696799],"domain_scores_gemma":[0.998433,0.0004070029,0.0001028854,0.0007459196,0.0001570338,0.0001541426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008895053,0.0000287804,0.001108623,0.00006451062,0.00003059816,0.00002235893,0.0002134949,0.7696062,0.0002120662,0.2266245,0.000004001583,0.002075969],"study_design_scores_gemma":[0.0002093295,0.00003014717,0.0002565188,0.0001937561,0.00004926649,0.000004996944,0.00007767315,0.9086719,0.0002866035,0.08949203,0.0003458571,0.0003819618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2464388,0.0001094125,0.7527319,0.00006287909,0.0001223462,0.0003030492,0.000006214232,0.0001423742,0.00008295219],"genre_scores_gemma":[0.8678849,0.0002873364,0.1314445,0.00007249363,0.0000569781,0.000004441236,0.000012203,0.00001989838,0.0002172703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6214461,"threshold_uncertainty_score":0.9999034,"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."}}