{"id":"W2034276439","doi":"","title":"On the number of inference regions of deep feed forward networks with piece-wise linear activations","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Piecewise linear function; Perceptron; Mathematics; Linear model; Deep learning; Inference; Rectifier (neural networks); Constant (computer programming); Infinity; Omega; Computer science; Combinatorics; Algorithm; Artificial neural network; Artificial intelligence; Mathematical analysis; Recurrent neural network; Statistics; Physics","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":[0.00329629,0.000776912,0.001306303,0.0008650243,0.0009661065,0.003216894,0.00312998,0.00172939,0.007252642],"category_scores_gemma":[0.02728019,0.001102288,0.001447611,0.0007172526,0.002655641,0.007953913,0.00346684,0.0041606,0.0006958147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002618087,"about_ca_system_score_gemma":0.001599093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002872133,"about_ca_topic_score_gemma":0.002983932,"domain_scores_codex":[0.9981377,0.0006105296,0.0001241058,0.000486875,0.0004290069,0.0002117673],"domain_scores_gemma":[0.9546144,0.03812449,0.002754506,0.001870775,0.001525572,0.00111024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008392008,0.0001633706,0.00652964,0.0006484236,0.0002262446,0.0004723315,0.0004144979,0.6417148,0.006101178,0.2986709,0.005131461,0.03908785],"study_design_scores_gemma":[0.00001907915,0.00003432548,0.0004985083,0.00003159369,0.00003094508,0.0000887696,0.00002580344,0.877833,0.00126045,0.1195133,0.0006489345,0.00001529547],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.247478,0.003080057,0.7246565,0.006859888,0.0001862431,0.00009313622,0.001022506,0.001006398,0.0156173],"genre_scores_gemma":[0.8879501,0.001163334,0.1024136,0.0006622056,0.000272468,0.0002218725,0.0008707211,0.0003991728,0.006046628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007252642,"threshold_uncertainty_score":0.02426249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03546629685649395,"score_gpt":0.1824907943954275,"score_spread":0.1470244975389335,"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."}}