{"id":"W4401052711","doi":"10.1016/j.neucom.2024.128275","title":"SITU: Stochastic input encoding and weight update thresholding for efficient memristive neural network in-situ training","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"In situ; Computer science; Encoding (memory); Artificial neural network; Thresholding; Artificial intelligence; Pattern recognition (psychology); Training (meteorology); Machine learning; Image (mathematics); Chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003609441,0.0003320489,0.0003499394,0.0001898703,0.0002813907,0.0001526117,0.000154303,0.00007475874,0.000001555633],"category_scores_gemma":[0.00005984168,0.0003478138,0.00008697291,0.0004636782,0.00003805853,0.0001627201,0.000142491,0.0005892289,0.000003254673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006820289,"about_ca_system_score_gemma":0.00001540436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.078753e-7,"about_ca_topic_score_gemma":0.000003025694,"domain_scores_codex":[0.9980443,0.00003767894,0.0004363525,0.00056225,0.0001436713,0.0007757066],"domain_scores_gemma":[0.9987867,0.0009030952,0.00004780346,0.0001285606,0.00002071934,0.0001130659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001292216,0.000004221855,0.00002376119,0.0001807718,0.00001341964,0.00007989003,0.001126767,0.9333857,0.02005914,0.000616256,0.00003382005,0.04446331],"study_design_scores_gemma":[0.0003364784,0.00004161752,0.0002300836,0.0005435761,0.00002202645,0.00008966673,0.0001031081,0.9944961,0.002942359,0.0004641379,0.0003891322,0.0003416836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7928854,0.001474957,0.2023833,0.00006653759,0.001615851,0.0004047937,0.000002135153,0.0007092761,0.0004577888],"genre_scores_gemma":[0.9958578,0.00001303201,0.002862714,0.0001344942,0.001016602,0.00001780094,0.00000470665,0.00008743434,0.000005351045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2029725,"threshold_uncertainty_score":0.9998974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02303172755659986,"score_gpt":0.255185661224727,"score_spread":0.2321539336681271,"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."}}