{"id":"W4386735370","doi":"10.1007/978-3-031-43520-1_8","title":"Genetic Algorithm for CNN Architecture Optimization","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Convolutional neural network; MNIST database; Computer science; Genetic algorithm; Pooling; Architecture; Artificial intelligence; Hyperparameter; Focus (optics); Algorithm; Deep learning; Pattern recognition (psychology); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004534657,0.0008162514,0.0008337049,0.000549114,0.0003372525,0.000554828,0.001144035,0.001578133,0.005076912],"category_scores_gemma":[0.001139032,0.0005586402,0.0006739878,0.0008173196,0.0004954413,0.0004879371,0.000601569,0.00126729,0.0009341358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008692,"about_ca_system_score_gemma":0.0008868673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01080428,"about_ca_topic_score_gemma":0.008817966,"domain_scores_codex":[0.999872,0.00003713535,0.00000467566,0.00002565313,0.00004189302,0.00001873066],"domain_scores_gemma":[0.9997599,0.0001397984,0.00001424918,0.0000171379,0.0000601651,0.000008705115],"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":[0.00001769073,0.00001497149,0.00009808668,0.000028939,0.00002632344,0.00002540236,0.00001519463,0.9131531,0.0008457636,0.006631783,0.002660561,0.07648214],"study_design_scores_gemma":[0.000004770495,0.000007568262,0.00004101028,0.000006262557,0.000004565319,0.000006828662,0.000002793629,0.995821,0.0001749299,0.00316532,0.0007626894,0.000002228497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008110929,0.001324202,0.9772936,0.0002677154,0.0001486093,0.00005121655,0.00006692548,0.0006546028,0.01208229],"genre_scores_gemma":[0.2751635,0.001261559,0.6963192,0.0003528095,0.0001687216,0.00042072,0.0003328839,0.0004364405,0.02554419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01080428,"threshold_uncertainty_score":0.02148283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01760286386522514,"score_gpt":0.2385212704245129,"score_spread":0.2209184065592878,"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."}}