{"id":"W4280643089","doi":"10.1609/aaai.v36i6.20558","title":"Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Defense Acquisition Program Administration; Agency for Defense Development","keywords":"Stiefel manifold; Orthogonality; Tangent bundle; Stability (learning theory); Gradient descent; Manifold (fluid mechanics); Computer science; Discretization; Mathematical optimization; Tangent vector; Mathematics; Applied mathematics; Tangent; Control theory (sociology); Algorithm; Tangent space; Artificial neural network; Artificial intelligence; Mathematical analysis; Machine learning; Geometry","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":[],"consensus_categories":[],"category_scores_codex":[0.000416805,0.0001277353,0.0001386621,0.00008362535,0.0005578278,0.0001738297,0.0005424349,0.00002352156,0.00007260466],"category_scores_gemma":[0.00007273278,0.00009683233,0.00004934152,0.0003906406,0.0001129046,0.0001968899,0.0002369722,0.0001516997,0.000003416648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005670468,"about_ca_system_score_gemma":0.00006605344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000126312,"about_ca_topic_score_gemma":0.00000321939,"domain_scores_codex":[0.9987589,0.00001691515,0.000280356,0.0003701956,0.0003565239,0.0002171389],"domain_scores_gemma":[0.9990772,0.00006038715,0.0002574955,0.0001225267,0.0004231724,0.00005921796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001657353,0.0003614287,0.0001345458,0.00006131319,0.00001857051,2.786483e-7,0.001551141,0.02674752,0.00403701,0.9375805,0.0001446313,0.0291973],"study_design_scores_gemma":[0.0001052924,0.000629243,0.0001309698,0.00008294001,0.00002359401,0.000009299719,0.001329162,0.8163232,0.1471228,0.03355945,0.0004183183,0.0002656982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4099382,0.00002232511,0.5843103,0.002294693,0.0003761096,0.001042874,0.00002878469,0.00009153669,0.001895213],"genre_scores_gemma":[0.9936239,0.00001134576,0.005964916,0.0001503861,0.0000209262,0.0001022326,0.00000242481,0.000007641785,0.0001162962],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9040211,"threshold_uncertainty_score":0.4290417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06031393677450669,"score_gpt":0.2617351034577038,"score_spread":0.2014211666831971,"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."}}