{"id":"W4382536871","doi":"10.1101/2023.06.28.546903","title":"Efficient Visual Perception of Human-Robot Walking Environments using Semi-Supervised Learning","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Waterloo; University of Toronto","funders":"AGE-WELL","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Deep learning; Machine learning; Software deployment; Inference; Robot; Supervised learning; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006364129,0.000778481,0.0005514097,0.0003960253,0.0002712428,0.0006653696,0.001279936,0.0006540826,0.001941943],"category_scores_gemma":[0.002099739,0.0004627465,0.0005555218,0.0003280897,0.000670943,0.000982065,0.000820715,0.0008357729,0.0008478513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005686212,"about_ca_system_score_gemma":0.0006793626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005667352,"about_ca_topic_score_gemma":0.009185536,"domain_scores_codex":[0.9995369,0.0001091156,0.00001758446,0.0001874485,0.00009885533,0.00005009878],"domain_scores_gemma":[0.9987043,0.0003754698,0.0001842804,0.0003209261,0.0003393407,0.00007569743],"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":[0.0005820863,0.0005031132,0.005220443,0.0002412353,0.0001768066,0.0002232549,0.0002179183,0.4736769,0.1113886,0.002147829,0.008617728,0.3970039],"study_design_scores_gemma":[0.000005352876,0.00002847763,0.001098277,0.000007004588,0.000004299738,0.00002360721,0.00001598625,0.9866678,0.01038176,0.001390156,0.0003687964,0.000008539527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1051221,0.0001250988,0.8853309,0.0001142344,0.00005557085,0.00006385415,0.0003755921,0.006882317,0.001930312],"genre_scores_gemma":[0.7987263,0.00006602288,0.1974789,0.0001295325,0.00002021997,0.00007513878,0.000933858,0.000247757,0.002322324],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005667352,"threshold_uncertainty_score":0.01126873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03208939583616948,"score_gpt":0.2736413938008779,"score_spread":0.2415519979647084,"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."}}