{"id":"W4317780736","doi":"10.1080/19420889.2022.2163131","title":"Biologically-inspired neuronal adaptation improves learning in neural networks","year":2023,"lang":"en","type":"article","venue":"Communicative & Integrative Biology","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Royal University; University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada","keywords":"Hebbian theory; Computer science; Artificial intelligence; MNIST database; Adaptation (eye); Artificial neural network; Perceptron; Machine learning; Backpropagation; Stability (learning theory); Convolutional neural network; Pattern recognition (psychology); Neuroscience; Psychology","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":[0.0006662008,0.0005313666,0.000297737,0.0002527064,0.0002243937,0.0005453684,0.0007790015,0.0006465772,0.001715185],"category_scores_gemma":[0.004433361,0.0001936756,0.0002687802,0.0002811934,0.0005793899,0.001188235,0.0009020782,0.001143716,0.0003932932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005247319,"about_ca_system_score_gemma":0.0003493135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001274967,"about_ca_topic_score_gemma":0.001231521,"domain_scores_codex":[0.9997602,0.00005490142,0.00001530835,0.00007556386,0.00006187714,0.00003220908],"domain_scores_gemma":[0.9991571,0.0004072109,0.0001112846,0.0001607269,0.0001188281,0.00004482215],"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":[0.0001935395,0.0002206451,0.003418491,0.0002152843,0.0001498637,0.0001882396,0.0002071398,0.5793133,0.1622652,0.02525018,0.002525712,0.2260524],"study_design_scores_gemma":[0.00001562663,0.0001596981,0.002334731,0.00001674189,0.00003246271,0.00006796612,0.00002275716,0.9396875,0.03068018,0.02419163,0.002768908,0.00002185289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.471507,0.002028673,0.5098202,0.001337141,0.0003978212,0.00005361131,0.00008715213,0.003248766,0.01151947],"genre_scores_gemma":[0.9622072,0.0003693769,0.03507342,0.0002076325,0.00005464586,0.00002408844,0.00005315738,0.000140526,0.001869897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001715185,"threshold_uncertainty_score":0.005737841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04879400398958043,"score_gpt":0.3076739811272455,"score_spread":0.258879977137665,"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."}}