{"id":"W7113065291","doi":"","title":"Systematic Exploration of Power-Augmented Feedforward Layers in Transformer Networks","year":2023,"lang":"en","type":"article","venue":"University Library (University of Saskatchewan)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Saskatchewan","keywords":"Perceptron; Feed forward; Artificial neural network; Transformer; Computation; Piecewise linear function; Stability (learning theory); Layer (electronics); Feedforward neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001157481,0.001046938,0.0004773817,0.0003581651,0.0002927269,0.001150444,0.001119944,0.0006375165,0.002565662],"category_scores_gemma":[0.005050824,0.0005552653,0.0004755068,0.0002548334,0.0007896214,0.002071187,0.001300218,0.001424106,0.0004211959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008511372,"about_ca_system_score_gemma":0.000955732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002199601,"about_ca_topic_score_gemma":0.004021103,"domain_scores_codex":[0.9995901,0.0001799042,0.0000213527,0.00005728912,0.0001074387,0.00004392053],"domain_scores_gemma":[0.9985768,0.0009834871,0.0000894027,0.0001669836,0.0001465665,0.00003678396],"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":[0.0001721143,0.00006153122,0.0009231849,0.0002301157,0.00003462967,0.0001836326,0.0001245304,0.8794404,0.008981113,0.02162324,0.0009826601,0.08724292],"study_design_scores_gemma":[0.000006887862,0.00003420883,0.00004897942,0.0000159519,0.000006476462,0.0000208,0.00001207132,0.9903027,0.002911306,0.006076706,0.0005608287,0.000003094116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1301007,0.0007340114,0.8577647,0.000373969,0.00004557439,0.0001047258,0.0001136145,0.00144651,0.009316152],"genre_scores_gemma":[0.8068433,0.0004529229,0.1901283,0.0001099663,0.00001120155,0.0001321445,0.0001396349,0.0002370675,0.001945531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002565662,"threshold_uncertainty_score":0.00858295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01049398077639254,"score_gpt":0.174498499655929,"score_spread":0.1640045188795364,"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."}}