{"id":"W2606766152","doi":"10.23977/jaip.2016.11005","title":"BLSTM Recurrent Neural Network for Object Recognition","year":2016,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Object (grammar); Representation (politics); Recurrent neural network; Fuse (electrical); Context (archaeology); Sequence (biology); Pattern recognition (psychology); Image (mathematics); Artificial neural network; Tree (set theory); Cognitive neuroscience of visual object recognition; Computer vision","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001250947,0.0001488297,0.0002103946,0.00009967365,0.0002054776,0.0001351383,0.0007445979,0.00006214223,0.00001974815],"category_scores_gemma":[0.002435309,0.0001049427,0.0001634452,0.0005297824,0.00006450514,0.002572323,0.00008996433,0.0002472271,0.0000893526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000902721,"about_ca_system_score_gemma":0.00009702393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001857657,"about_ca_topic_score_gemma":0.000006315515,"domain_scores_codex":[0.9979928,0.0001793925,0.0008537931,0.0002743228,0.0003389329,0.0003607547],"domain_scores_gemma":[0.9938442,0.003487683,0.001176802,0.0003297977,0.001011865,0.0001496363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00021105,0.0001187777,0.000007424084,0.000003462776,0.00002234132,0.00001024196,0.0001124012,0.001950087,0.001942843,0.0239063,0.001750393,0.9699647],"study_design_scores_gemma":[0.0002414103,0.002277573,0.00006109876,0.0003018675,0.0001622374,0.001114301,0.0002993914,0.06673808,0.06384546,0.7145958,0.1496518,0.0007110019],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001943509,0.0002255473,0.9784831,0.01709056,0.001749546,0.0002865417,0.000003989098,0.00004392288,0.0001733135],"genre_scores_gemma":[0.3233408,0.0007691743,0.6715561,0.001323426,0.00287263,0.00004785211,0.000001339124,0.00002621232,0.00006240115],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9692537,"threshold_uncertainty_score":0.4279439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09685038027984123,"score_gpt":0.3657783224103479,"score_spread":0.2689279421305066,"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."}}