{"id":"W2577073647","doi":"10.1109/ictai.2016.0069","title":"Improving Deep Belief Networks via Delta Rule for Sentiment Classification","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Deep belief network; Boltzmann machine; Computer science; Artificial intelligence; Restricted Boltzmann machine; Layer (electronics); Artificial neural network; Deep learning; Backpropagation; Sentiment analysis; Machine learning; Unsupervised learning; Pattern recognition (psychology); Natural language processing","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":[0.002011349,0.0009933795,0.001045318,0.001018961,0.0003826965,0.001001754,0.001549605,0.0009261505,0.001467935],"category_scores_gemma":[0.006185317,0.0004565363,0.000706306,0.0007945407,0.0004149125,0.001853864,0.001043121,0.00224239,0.0009342089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007350445,"about_ca_system_score_gemma":0.0008723543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003964249,"about_ca_topic_score_gemma":0.004313994,"domain_scores_codex":[0.9991689,0.0002192561,0.00008375959,0.0001692003,0.0002746463,0.00008426129],"domain_scores_gemma":[0.9982184,0.000765493,0.0001576708,0.0001621522,0.0006287148,0.00006765544],"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":[0.0002674038,0.000289749,0.003748399,0.0001382186,0.0001478692,0.000122778,0.00009515347,0.2939854,0.008661843,0.007572407,0.004650909,0.68032],"study_design_scores_gemma":[0.000007365865,0.00002180384,0.0001206763,0.000005430933,0.000008474737,0.000008262274,0.000004429176,0.9960815,0.001162857,0.002322464,0.0002533231,0.000003377811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05500163,0.0009107083,0.9387097,0.0003960613,0.0001940484,0.00007984446,0.0001448137,0.001711302,0.002851836],"genre_scores_gemma":[0.6855514,0.0007005762,0.3079783,0.0005061185,0.0001591214,0.0001693083,0.0008837346,0.0001722224,0.003879191],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003964249,"threshold_uncertainty_score":0.0106371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0200385010352133,"score_gpt":0.2538341298858324,"score_spread":0.2337956288506191,"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."}}