{"id":"W2760804696","doi":"10.1109/cjece.2017.2703093","title":"ZIZO: A Novel Zoom-In–Zoom-Out Search Algorithm for the Global Parameters of Echo-State Networks","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Electrical and Computer Engineering","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Zoom; Computer science; Echo state network; Algorithm; Echo (communications protocol); Recurrent neural network; Representation (politics); State (computer science); Sampling (signal processing); Artificial intelligence; Artificial neural network; Computer vision","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008985855,0.001233464,0.001154961,0.0009590111,0.0005309706,0.0006690052,0.002296282,0.001540497,0.003716219],"category_scores_gemma":[0.003727385,0.0007203182,0.0006681611,0.0006907824,0.0007266804,0.001491324,0.001604033,0.001591031,0.0007960211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006324647,"about_ca_system_score_gemma":0.001266102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006627104,"about_ca_topic_score_gemma":0.01131501,"domain_scores_codex":[0.9996594,0.00005858948,0.00002418891,0.00007752502,0.0001373113,0.0000430204],"domain_scores_gemma":[0.9993574,0.0003178887,0.00009096378,0.00007120334,0.0001208328,0.00004171157],"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":[0.0006293533,0.0001661428,0.002325227,0.0003832094,0.000177092,0.0002320609,0.0003820626,0.3255667,0.04245963,0.01169216,0.00985728,0.6061291],"study_design_scores_gemma":[0.00006668838,0.00004095626,0.0002481482,0.00001392566,0.00001488531,0.00005251672,0.00002093424,0.9898208,0.005137216,0.002602806,0.00196282,0.00001814201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007147187,0.0002356393,0.9896705,0.00008126711,0.0000303025,0.00006799018,0.00004157441,0.002171776,0.0005538697],"genre_scores_gemma":[0.1337707,0.0001785356,0.8633881,0.0002205352,0.00002713218,0.0002665638,0.0002362428,0.0004742746,0.001438028],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006627104,"threshold_uncertainty_score":0.0131771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647081047794781,"score_gpt":0.2261381760806311,"score_spread":0.2096673656026833,"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."}}