{"id":"W4387016597","doi":"10.22541/au.169564699.96503493/v1","title":"On training spiking neural networks by means of a novel quantum inspired machine learning method","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada)","funders":"","keywords":"MNIST database; Artificial neural network; Artificial intelligence; Computer science; Spiking neural network; Set (abstract data type); Types of artificial neural networks; Deep neural networks; Machine learning; Deep learning; Quantum; Differentiable function; Spike (software development); Training set; Recurrent neural network; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001635134,0.0006070965,0.0009619102,0.0003043767,0.0002711065,0.0003494608,0.002409056,0.0004005173,0.00000715124],"category_scores_gemma":[0.0001859256,0.000512197,0.0004384354,0.0007900344,0.00005415709,0.0001564867,0.004072777,0.002643537,0.000002555489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005691581,"about_ca_system_score_gemma":0.00006592013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006789874,"about_ca_topic_score_gemma":0.00005423032,"domain_scores_codex":[0.9956968,0.0003963213,0.0009582887,0.001374008,0.0006927171,0.0008818462],"domain_scores_gemma":[0.9966266,0.001338446,0.0007680109,0.0009522581,0.0001171799,0.0001975751],"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":[0.00001295581,0.00006092077,0.00008194926,0.00006846862,0.00007825539,0.00002756565,0.0005184757,0.9595482,0.000232826,0.007059122,0.0005471079,0.03176416],"study_design_scores_gemma":[0.0004506268,0.0001837827,0.00007729766,0.0004695693,0.00001864338,0.00001493127,0.00003426748,0.9965878,0.00007248598,0.001370853,0.0001968942,0.0005229183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008812954,0.0003308601,0.9854842,0.001166677,0.002371626,0.0003622381,0.000007447166,0.0009358301,0.0005281708],"genre_scores_gemma":[0.8794855,0.00005814223,0.1188766,0.0004812943,0.000406741,0.00002220246,0.00006208683,0.0001036624,0.0005037807],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8706726,"threshold_uncertainty_score":0.999733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07902064771317191,"score_gpt":0.3089316892097626,"score_spread":0.2299110414965907,"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."}}