{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00389743,0.001420699,0.001404938,0.001125424,0.0005081854,0.001358604,0.003246673,0.00185519,0.001710021],"category_scores_gemma":[0.007084669,0.001070632,0.001450996,0.001420824,0.002023485,0.00347491,0.003113655,0.003390574,0.0006189697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008758474,"about_ca_system_score_gemma":0.00118068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003691948,"about_ca_topic_score_gemma":0.004726877,"domain_scores_codex":[0.9974879,0.001461324,0.00008695116,0.0004326163,0.0004001085,0.0001310853],"domain_scores_gemma":[0.9973972,0.001582977,0.000213794,0.0003833951,0.000312496,0.0001101729],"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":[0.0001194381,0.0000845525,0.00157925,0.0001636605,0.0002293617,0.000115032,0.0001689002,0.6986511,0.002032828,0.1447877,0.002984475,0.1490836],"study_design_scores_gemma":[0.000004985919,0.00002347104,0.00007920357,0.000009076288,0.000007924168,0.00001824464,0.000005705551,0.9628166,0.0002577311,0.03606269,0.0007051979,0.00000919879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001192915,0.0001394816,0.9981638,0.0001039638,0.00001176698,0.0000100335,0.00003397642,0.0001398199,0.0002042446],"genre_scores_gemma":[0.2586867,0.0009708275,0.7334967,0.0005328495,0.0002744812,0.0004625516,0.0006790287,0.0002572659,0.004639625],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00389743,"threshold_uncertainty_score":0.02061182,"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."}}