{"id":"W2963654998","doi":"10.1109/icra.2016.7487176","title":"Deep learning for tactile understanding from visual and haptic data","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Tactile and Sensory Interactions","field":"Neuroscience","cited_by":253,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Public Health Agency of Canada; National Science Foundation","keywords":"Haptic technology; Computer science; Robot; Artificial intelligence; Human–computer interaction; Object (grammar); Domain (mathematical analysis); Visualization; Computer vision","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006963445,0.001139322,0.0007827186,0.0006409236,0.0002863478,0.0009906136,0.001430404,0.001704033,0.002423927],"category_scores_gemma":[0.00261627,0.0005486907,0.0009191906,0.0006264694,0.0007509774,0.002246312,0.001635606,0.002614684,0.0006226366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008136957,"about_ca_system_score_gemma":0.0006585606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00359877,"about_ca_topic_score_gemma":0.004440546,"domain_scores_codex":[0.9997349,0.00005186367,0.00001492435,0.00009231849,0.00005274999,0.00005318795],"domain_scores_gemma":[0.9992873,0.0003687033,0.0000834958,0.00009685617,0.0001085097,0.00005510903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003105251,0.0002987761,0.00298976,0.0003271255,0.0001953091,0.0001959686,0.0001761707,0.5230227,0.02088275,0.01814335,0.006700216,0.4267574],"study_design_scores_gemma":[0.000005023089,0.00001833956,0.0002465304,0.000007461931,0.00000719481,0.00001266503,0.000009448772,0.9883479,0.001347536,0.009743063,0.0002504316,0.0000043918],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07569661,0.001303901,0.9158733,0.00121883,0.0001177456,0.00004523634,0.000363235,0.001762207,0.003618903],"genre_scores_gemma":[0.8791448,0.0006961109,0.1132119,0.0004516169,0.0001153779,0.0001229871,0.0009524567,0.000108581,0.005196156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00359877,"threshold_uncertainty_score":0.008108795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2105668897559384,"score_gpt":0.3700275053479651,"score_spread":0.1594606155920266,"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."}}