{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004114751,0.0004494245,0.000654467,0.0002141718,0.0003433134,0.0003239817,0.0007183646,0.0002026395,0.000001643206],"category_scores_gemma":[0.00003479502,0.0004171205,0.0001808309,0.0001352977,0.00009268613,0.0001918275,0.0002835842,0.0004944591,0.000008002804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006624984,"about_ca_system_score_gemma":0.0000235461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001115602,"about_ca_topic_score_gemma":0.00001383946,"domain_scores_codex":[0.9975033,0.00003815725,0.0008422146,0.0008869945,0.000195017,0.0005343354],"domain_scores_gemma":[0.9970471,0.001847186,0.0004396622,0.0004749398,0.0000697112,0.0001214399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002509167,0.00001116107,0.0000198837,0.0001230564,0.00003295437,0.00001897458,0.0001629026,0.2939858,0.00000869896,0.376469,0.0003252144,0.3288173],"study_design_scores_gemma":[0.0002719151,0.0001035627,0.000003243035,0.00102634,0.00001042061,0.00002362531,0.00007011632,0.8340639,0.000004260034,0.002298822,0.1617255,0.0003982972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002952394,0.01438722,0.9578983,0.0004068218,0.002640902,0.00272599,0.00002362751,0.0004339952,0.02118791],"genre_scores_gemma":[0.9215953,0.005774407,0.006163952,0.001311575,0.00494795,0.0005276732,0.0001388326,0.0003733129,0.05916694],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9517344,"threshold_uncertainty_score":0.999828,"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."}}