{"id":"W2397184916","doi":"","title":"Hybrid orthogonal projection and estimation (HOPE): a new framework to learn neural networks","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"MNIST database; Computer science; Artificial intelligence; TIMIT; Unsupervised learning; Projection (relational algebra); Artificial neural network; Machine learning; Feature (linguistics); Generative model; Pattern recognition (psychology); Generative grammar; Hidden Markov model; Algorithm","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":[0.003099784,0.0001044078,0.0001831749,0.0005684133,0.0002590099,0.0003109138,0.0004054925,0.00006214664,0.0001210865],"category_scores_gemma":[0.004281899,0.00006797117,0.00007015526,0.0004905472,0.00004415295,0.0005466442,0.0001984045,0.00105058,0.00004278532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007364948,"about_ca_system_score_gemma":0.0001300702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003422932,"about_ca_topic_score_gemma":0.00000563678,"domain_scores_codex":[0.9976577,0.0006302999,0.0003260068,0.000228281,0.0008154119,0.0003422909],"domain_scores_gemma":[0.9977841,0.001263771,0.0001633901,0.0001582435,0.0003055201,0.0003249683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009675166,0.00002505432,0.004252437,0.000004402797,0.00001481548,0.00004947079,0.0001478602,0.001349839,0.0002360122,0.0004023325,0.001190724,0.9922303],"study_design_scores_gemma":[0.000784846,0.001424884,0.01575617,0.0003942277,0.000008919439,0.001337306,0.0000324718,0.9597686,0.0006181842,0.006664558,0.01299008,0.0002197917],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1796078,0.0001739421,0.8075784,0.01213501,0.0001878615,0.0001099133,3.017155e-7,0.00003599912,0.0001707706],"genre_scores_gemma":[0.9035174,0.0001196107,0.09455599,0.0001594739,0.0004596113,0.000004647287,3.500604e-7,0.00001517912,0.001167752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9920105,"threshold_uncertainty_score":0.5126143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04822904721375278,"score_gpt":0.353960200129276,"score_spread":0.3057311529155232,"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."}}