{"id":"W4312223971","doi":"10.3389/fcomp.2022.1066422","title":"An intrinsically motivated learning algorithm based on Bayesian surprise for cognitive radar in autonomous vehicles","year":2022,"lang":"en","type":"article","venue":"Frontiers in Computer Science","topic":"Cognitive Science and Education Research","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; University of Toronto","funders":"Ministère de la Défense Nationale","keywords":"Surprise; Computer science; Radar; Kalman filter; Robustness (evolution); Algorithm; Artificial intelligence; Machine learning; Bayesian probability","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002331165,0.0001546315,0.0001978896,0.001293831,0.0008858339,0.0002413721,0.001109815,0.00002910077,0.00003050187],"category_scores_gemma":[0.0008522805,0.0001641569,0.00004340314,0.003583483,0.0007326423,0.0005435376,0.0002444637,0.0005405452,0.000004118171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004212233,"about_ca_system_score_gemma":0.0009816831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003633733,"about_ca_topic_score_gemma":0.000003476806,"domain_scores_codex":[0.9964734,0.0005006909,0.0002687536,0.001102168,0.0009197285,0.0007352055],"domain_scores_gemma":[0.9987212,0.0006139999,0.00008442561,0.0002407915,0.0001340632,0.0002054561],"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":[0.0001412654,0.0007264438,0.02128576,0.000006552091,8.536848e-7,0.00005902744,0.001713942,0.02102437,0.004013147,0.00006105578,0.0002722781,0.9506953],"study_design_scores_gemma":[0.0008690874,0.0008149882,0.01696035,0.0000239926,0.000001074209,0.000003583074,0.0005813881,0.9673622,0.01227846,0.0005380718,0.0003571048,0.0002097229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2994645,0.000006132477,0.6980986,0.0006153506,0.001021233,0.0006135275,0.00002214642,0.00005685988,0.0001017008],"genre_scores_gemma":[0.9508751,0.000002459589,0.04758571,0.001276268,0.00005667839,0.0001461202,0.000007615804,0.00001238708,0.00003763595],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9504856,"threshold_uncertainty_score":0.6813207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02372715477794828,"score_gpt":0.3060949669974538,"score_spread":0.2823678122195055,"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."}}