{"id":"W4287766314","doi":"10.48550/arxiv.2006.01765","title":"AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane\\n Sensor Processors","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"CCD and CMOS Imaging Sensors","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"MNIST database; Computer science; Convolutional neural network; Robustness (evolution); Computation; Image processing; Computer hardware; Efficient energy use; Artificial intelligence; Artificial neural network; Algorithm; Engineering; Image (mathematics); Electrical engineering","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":[0.0003243663,0.0007445425,0.0002639274,0.000412067,0.0002381672,0.000563915,0.001521106,0.0007259951,0.00573923],"category_scores_gemma":[0.001020829,0.0003304935,0.0002828678,0.0004154092,0.0004100634,0.001028862,0.0006503391,0.0007220302,0.0010938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133514,"about_ca_system_score_gemma":0.001017012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01663923,"about_ca_topic_score_gemma":0.02926014,"domain_scores_codex":[0.9998485,0.00001727486,0.000006225176,0.00005498675,0.00004673078,0.00002629349],"domain_scores_gemma":[0.9998338,0.00004710734,0.00001616464,0.00003768074,0.00005302385,0.00001216552],"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":[0.000278092,0.000142411,0.001561848,0.0002072084,0.0001297151,0.0001601887,0.0000376788,0.536382,0.01847674,0.01584152,0.02408041,0.4027021],"study_design_scores_gemma":[0.000008780643,0.00002425105,0.0001840681,0.000008299507,0.00000687564,0.00001899474,0.000003524274,0.9890038,0.005729026,0.002430002,0.0025774,0.000004848443],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06000565,0.001084971,0.9083091,0.0007492198,0.0004034598,0.0001248852,0.001184939,0.01477385,0.01336396],"genre_scores_gemma":[0.631917,0.0006229965,0.3369451,0.0006523926,0.0001149844,0.0001998326,0.002739183,0.0003949127,0.02641355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01663923,"threshold_uncertainty_score":0.03308475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06596700210387972,"score_gpt":0.1859195734714423,"score_spread":0.1199525713675626,"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."}}