{"id":"W2141399712","doi":"","title":"Learning to combine foveal glimpses with a third-order Boltzmann machine","year":2010,"lang":"en","type":"article","venue":"","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":427,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Foveal; Computer science; Artificial intelligence; Boltzmann machine; Pixel; Fixation (population genetics); Computer vision; Image (mathematics); Pattern recognition (psychology); Machine learning; Deep learning; Retinal","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001392042,0.0001490068,0.0001400689,0.00005644536,0.00007113886,0.0000409973,0.00018296,0.00009492578,0.0001638096],"category_scores_gemma":[0.00009603385,0.0001133577,0.00005586558,0.0001487186,0.0000472192,0.000003341597,0.0001531231,0.0002077501,0.00003288289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000330498,"about_ca_system_score_gemma":0.00002745049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000182908,"about_ca_topic_score_gemma":0.001572223,"domain_scores_codex":[0.999202,0.00002187615,0.0001278095,0.0003238199,0.0001158784,0.0002086724],"domain_scores_gemma":[0.9993173,0.000007446442,0.0000413778,0.0003935651,0.0001400742,0.0001002765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006282001,0.00006566159,0.005928611,0.000003990026,0.00005328457,0.000005477536,0.0000282836,0.00001906854,0.983021,0.00005821564,0.007802682,0.002950938],"study_design_scores_gemma":[0.0003206279,0.000754943,0.001000589,0.00000340582,0.00003084191,0.00002477122,0.00004697885,0.0001829537,0.8697532,0.00002309818,0.1276266,0.000231927],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9563691,0.00004532624,0.01047629,0.0004290901,0.00001574205,0.0001640578,0.000001110889,0.0001031613,0.03239612],"genre_scores_gemma":[0.9707072,0.00001579105,0.01520449,0.0009504894,0.00009083389,0.00002204705,0.00008086148,0.00002823838,0.01290008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.119824,"threshold_uncertainty_score":0.4622594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002863944186778172,"score_gpt":0.2387524918759173,"score_spread":0.2358885476891391,"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."}}