{"id":"W1744468441","doi":"10.1109/iscas.1999.777648","title":"An in-the-loop training method for VLSI neural networks","year":2003,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial neural network; Computer science; Physical neural network; Activation function; Time delay neural network; Realization (probability); Quantization (signal processing); Very-large-scale integration; Artificial intelligence; Types of artificial neural networks; Algorithm; Embedded system; Mathematics","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":[0.0002475867,0.0003170738,0.0002380861,0.000176775,0.0002405676,0.0002727773,0.0007185233,0.0004040905,0.003417968],"category_scores_gemma":[0.0009181521,0.0001518703,0.0001634477,0.0002135224,0.0003354902,0.0005226523,0.0002960426,0.0006636151,0.0006186411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002619657,"about_ca_system_score_gemma":0.0002268439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006719105,"about_ca_topic_score_gemma":0.001016846,"domain_scores_codex":[0.9998412,0.0000362038,0.000007685215,0.00002937294,0.00007440228,0.00001113855],"domain_scores_gemma":[0.9998094,0.00008829582,0.00001578474,0.00003476243,0.00004411649,0.000007705981],"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":[0.0001489447,0.0001049453,0.0003448553,0.0001831579,0.00004255307,0.00008805336,0.0001569065,0.183846,0.06161483,0.05347855,0.003332027,0.6966593],"study_design_scores_gemma":[0.00001915448,0.00009716858,0.0001389337,0.00001908928,0.00001350282,0.000112835,0.000008589325,0.9535227,0.02222801,0.01017996,0.01364954,0.00001034288],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002607556,0.00008097908,0.9950678,0.0000458701,0.00003731525,0.00001742421,0.000007881995,0.0003678173,0.001767402],"genre_scores_gemma":[0.2050847,0.0002458471,0.7863384,0.0001355024,0.00007617543,0.0001618891,0.00004796303,0.0001384728,0.007771076],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003417968,"threshold_uncertainty_score":0.01143426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05447505194989972,"score_gpt":0.3331176544449864,"score_spread":0.2786426024950867,"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."}}