{"id":"W4375824959","doi":"10.1007/978-3-031-28332-1_7","title":"Tuning Neural Networks for Superior Accuracy on Resource-Constrained Edge Microcontrollers","year":2023,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Verafin (Canada)","funders":"","keywords":"Microcontroller; Computer science; Pruning; Artificial neural network; Quantization (signal processing); Enhanced Data Rates for GSM Evolution; Context (archaeology); Embedded system; Artificial intelligence; Computer engineering; Machine learning; Algorithm","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":[0.0002599093,0.0004816013,0.00042414,0.0002519255,0.000272334,0.0007409885,0.001332934,0.0006334405,0.00776069],"category_scores_gemma":[0.001456495,0.0002117289,0.0001717868,0.0004066946,0.0002062033,0.0009612687,0.0004550703,0.0009073733,0.001353012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004973834,"about_ca_system_score_gemma":0.0002830359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001391426,"about_ca_topic_score_gemma":0.00415472,"domain_scores_codex":[0.9997697,0.00003346973,0.0000151512,0.00006354328,0.00008021316,0.00003787976],"domain_scores_gemma":[0.9996508,0.0001626316,0.00003138134,0.00005818034,0.00008543651,0.00001157027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004176583,0.0001416154,0.0009979057,0.0004001975,0.00008130846,0.0001412327,0.0001034838,0.2692305,0.1059451,0.01951489,0.01078522,0.5922408],"study_design_scores_gemma":[0.00002646743,0.0001559292,0.0006948211,0.00005400783,0.00003475815,0.00009496955,0.00003259495,0.9375132,0.04117233,0.008893565,0.0113098,0.0000176774],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1117808,0.003529428,0.8323401,0.0005960654,0.0006091117,0.00008541228,0.0001781672,0.003213357,0.04766756],"genre_scores_gemma":[0.8340721,0.0006120379,0.1475059,0.0003387292,0.00009537781,0.00005858263,0.0001270614,0.0002885202,0.0169017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00776069,"threshold_uncertainty_score":0.02596211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02719678057684018,"score_gpt":0.2764830643194877,"score_spread":0.2492862837426475,"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."}}