{"id":"W4380558639","doi":"10.48550/arxiv.2306.06968","title":"Can Forward Gradient Match Backpropagation?","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Sorbonne Université; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; Compute Canada","keywords":"Backpropagation; Artificial neural network; Computer science; Computation; Isotropy; Gradient descent; Noise (video); Gradient method; Artificial intelligence; Algorithm; Physics; Image (mathematics); Optics","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":[0.004207855,0.001370295,0.001502341,0.0008886225,0.0005608241,0.002498295,0.00189687,0.003998432,0.007423568],"category_scores_gemma":[0.0318564,0.0007661449,0.0005667552,0.0008597985,0.002764872,0.01078295,0.00229316,0.003077881,0.004328791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008449877,"about_ca_system_score_gemma":0.001043426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0024964,"about_ca_topic_score_gemma":0.002213256,"domain_scores_codex":[0.9984768,0.0004107233,0.00007553591,0.0004254635,0.0004669692,0.0001444849],"domain_scores_gemma":[0.9965844,0.001937254,0.0002524198,0.0005960803,0.0004873958,0.0001423335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005647888,0.0001568082,0.002645037,0.0006691663,0.0002779314,0.0002361294,0.0002823261,0.09965649,0.006259952,0.4342445,0.0240824,0.4309244],"study_design_scores_gemma":[0.00006054656,0.000115232,0.0004755734,0.0001907139,0.00004956794,0.000256879,0.00006970329,0.3484025,0.00534776,0.6264022,0.01857605,0.00005325039],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01333251,0.004641765,0.9545331,0.008572535,0.001619565,0.00008068609,0.0001230027,0.001843218,0.01525365],"genre_scores_gemma":[0.5365316,0.006742049,0.4174357,0.006085296,0.001624428,0.000260111,0.0003324273,0.002243662,0.02874482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007423568,"threshold_uncertainty_score":0.02483433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0851859728657592,"score_gpt":0.2083090153710565,"score_spread":0.1231230425052973,"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."}}