{"id":"W4210327302","doi":"10.1017/s0269888921000151","title":"Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots","year":2022,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Norges Forskningsråd","keywords":"Neuroevolution; Computer science; Pruning; Modular design; Robustness (evolution); Artificial intelligence; Adaptability; Artificial neural network; Robot; Generalization; Machine learning; Mathematics","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":[0.0004865134,0.0001917312,0.0003084408,0.00004890321,0.0003268914,0.00001714064,0.000138639,0.00001602088,0.000008920211],"category_scores_gemma":[0.00012202,0.0001654194,0.0000638031,0.000214102,0.00002004817,0.00004441198,0.0001472398,0.0002609261,0.000001531508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005793996,"about_ca_system_score_gemma":0.000009382696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.939186e-7,"about_ca_topic_score_gemma":1.293862e-7,"domain_scores_codex":[0.9991798,0.00003876794,0.0002236764,0.0002029172,0.00008400287,0.0002708712],"domain_scores_gemma":[0.9994983,0.0002043738,0.00003221983,0.0001766986,0.00002274079,0.0000656373],"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":[0.000002970801,0.000004463702,9.943415e-7,0.001685591,0.00001965284,0.00000184838,0.0001260556,0.975649,0.002042719,0.0003052628,0.0001152173,0.0200462],"study_design_scores_gemma":[0.0002926216,0.00002428331,0.00005001754,0.0005458673,0.00006443538,0.0000632387,0.00001855085,0.9649662,0.0001468958,0.00001349293,0.03361996,0.0001944143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.04661364,0.7231191,0.2262332,0.0004303718,0.001121224,0.00150848,0.00000966132,0.0006550575,0.0003092931],"genre_scores_gemma":[0.9875985,0.009200047,0.002316091,0.000101066,0.0002102496,0.000310931,0.00000528486,0.00009459916,0.0001632774],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9409848,"threshold_uncertainty_score":0.6745609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01838925561508074,"score_gpt":0.2297927903447874,"score_spread":0.2114035347297067,"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."}}