{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000477357,0.000591301,0.00049368,0.0001768868,0.0002467358,0.0005579455,0.001424338,0.0008537556,0.004735338],"category_scores_gemma":[0.001255051,0.0004127932,0.0003141986,0.000227768,0.0003536798,0.0009570231,0.001591184,0.001255545,0.0009941781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002767214,"about_ca_system_score_gemma":0.0004441572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007444602,"about_ca_topic_score_gemma":0.002215052,"domain_scores_codex":[0.9998187,0.00003891915,0.00001202788,0.00003364553,0.00007678254,0.00001989715],"domain_scores_gemma":[0.9996525,0.000142041,0.00003439652,0.00007302071,0.0000730931,0.00002496917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000532079,0.0003091687,0.001037578,0.0003251507,0.0001213158,0.000215266,0.0002177187,0.3079359,0.1317362,0.02668682,0.007946086,0.5229368],"study_design_scores_gemma":[0.00001179923,0.00006019948,0.00007552542,0.000008821832,0.000006981353,0.00003734236,0.00001018409,0.9775489,0.01870952,0.002467287,0.001057995,0.00000551793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01578614,0.0001097768,0.9803723,0.00009803215,0.00008153997,0.00002757053,0.00005299929,0.001520966,0.001950861],"genre_scores_gemma":[0.5890102,0.0001411305,0.4002755,0.0002362099,0.00006568602,0.0001568993,0.0002652022,0.0005923582,0.009256706],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004735338,"threshold_uncertainty_score":0.01584131,"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."}}