{"id":"W4200633083","doi":"","title":"Hierarchical Sparse Dictionaries: how sparsity, topology and pooling can improve visual place recognition","year":2021,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"NeuroDevNet","funders":"","keywords":"Pooling; Computer science; Artificial intelligence; Pattern recognition (psychology); Sparse matrix; Topology (electrical circuits); Mathematics; Combinatorics","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002367838,0.0003668577,0.0004449319,0.0002352465,0.0004686876,0.001112081,0.001138003,0.0003900367,0.00002325249],"category_scores_gemma":[0.001896869,0.0004135058,0.0001555237,0.00040197,0.0003879224,0.0004895136,0.003956336,0.001113547,0.000004050403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001472181,"about_ca_system_score_gemma":0.0004074329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005718542,"about_ca_topic_score_gemma":0.0007855695,"domain_scores_codex":[0.9946963,0.002874207,0.0003947933,0.001204729,0.000398376,0.0004315536],"domain_scores_gemma":[0.9949598,0.001276224,0.0004141739,0.001437824,0.001669551,0.0002423789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000464404,0.000913319,0.001479917,0.0004132581,0.0001996952,0.0001175172,0.01564006,0.00002548604,0.01027638,0.0707359,0.0007617035,0.8993903],"study_design_scores_gemma":[0.001828925,0.00001302266,0.003880248,0.004035051,0.0001732246,0.000340835,0.0008565603,0.1305602,0.7135894,0.1242921,0.01775215,0.002678282],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05547753,0.0009471382,0.9214952,0.01870643,0.0003365872,0.0003849021,0.00004579442,0.0004999992,0.002106441],"genre_scores_gemma":[0.6403016,0.002325285,0.3545085,0.000359137,0.00006885656,0.00006976057,0.000432255,0.00003879102,0.001895766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8967121,"threshold_uncertainty_score":0.9999248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01877233891185356,"score_gpt":0.2535029408272274,"score_spread":0.2347306019153738,"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."}}