{"id":"W4292632476","doi":"10.1007/978-3-030-98347-5_19","title":"Efficient Approximate DNN Accelerators for Edge Devices: An Experimental Study","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"GaN-based semiconductor devices and materials","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Inference; Multiplier (economics); Deep neural networks; Computation; Computer science; Edge device; Enhanced Data Rates for GSM Evolution; Function (biology); Artificial neural network; Algorithm; Computer engineering; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002297437,0.0005698628,0.0006423736,0.0001134721,0.0003196664,0.000197174,0.0004392836,0.00008601743,0.02896767],"category_scores_gemma":[5.895245e-7,0.0005116003,0.0002609443,0.00002400908,0.00003355972,0.00008525843,0.0002127756,0.000184386,0.00005028995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008968457,"about_ca_system_score_gemma":0.00010033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001808015,"about_ca_topic_score_gemma":0.00001031748,"domain_scores_codex":[0.997977,0.00003317781,0.0005322815,0.0007831838,0.0002937285,0.0003806156],"domain_scores_gemma":[0.9988239,0.00004586948,0.0003212497,0.0005738123,0.00006871962,0.000166474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005093572,0.01033172,0.0009613718,0.0004702017,0.002302649,0.00002551537,0.009012106,0.0007400603,0.03789162,0.9273025,0.006987882,0.003464992],"study_design_scores_gemma":[0.00740878,0.005553527,0.0000281806,0.0001384923,0.001041324,0.000003058984,0.03165138,0.001089264,0.05242621,0.003108502,0.8928109,0.004740414],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6974477,0.0001645321,0.00008029235,0.00001131553,0.001718179,0.004251395,0.001208799,0.0001721146,0.2949456],"genre_scores_gemma":[0.9346529,5.13196e-7,0.0002154564,0.0001161981,0.0008533913,0.0007217781,0.0009767297,0.000178236,0.06228481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.924194,"threshold_uncertainty_score":0.9997336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04179005161943671,"score_gpt":0.2896277489400447,"score_spread":0.247837697320608,"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."}}