{"id":"W2161388792","doi":"10.48550/arxiv.1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":572,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Rectifier (neural networks); Piecewise linear function; Computer science; Computation; Artificial neural network; Feedforward neural network; Feed forward; Deep learning; Activation function; Homogeneous space; Artificial intelligence; Algorithm; Mathematics; Stochastic neural network; Recurrent neural network","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":[0.002759005,0.0011766,0.001470566,0.001329507,0.0009707934,0.003654542,0.002385795,0.001853757,0.005993531],"category_scores_gemma":[0.0300495,0.001091838,0.001597303,0.00101277,0.003563526,0.01222001,0.003792515,0.004644072,0.0006920999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002248689,"about_ca_system_score_gemma":0.001171293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001657699,"about_ca_topic_score_gemma":0.001364908,"domain_scores_codex":[0.9979005,0.0006884593,0.0001141299,0.0004688893,0.0005373074,0.0002906816],"domain_scores_gemma":[0.9635846,0.03023596,0.002131129,0.001894459,0.001040574,0.001113289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008894222,0.0001533805,0.005149277,0.000596708,0.0001365654,0.0003354726,0.000640203,0.3290299,0.006796742,0.6225513,0.004081494,0.02963956],"study_design_scores_gemma":[0.00003952495,0.00005820339,0.0005778075,0.00003803884,0.00002575585,0.00008455357,0.00004818007,0.4720912,0.001419705,0.5245247,0.001067354,0.00002500019],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3339628,0.003666758,0.6323458,0.0051826,0.0001382105,0.0001398044,0.001305672,0.0009966564,0.0222618],"genre_scores_gemma":[0.9145477,0.001494419,0.07568835,0.0005096213,0.0002535342,0.0002911245,0.0008751146,0.0004835291,0.005856522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005993531,"threshold_uncertainty_score":0.02005041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05273342306533113,"score_gpt":0.198821311659622,"score_spread":0.1460878885942908,"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."}}