{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004752928,0.00008478332,0.000110617,0.00003274271,0.00007036703,0.000002341986,0.0001451999,0.00003609009,0.00001724187],"category_scores_gemma":[0.00004360874,0.00006769725,0.00003859026,0.0003401386,0.0000570421,0.00009251597,0.00002735347,0.0001476576,0.000004310325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001623749,"about_ca_system_score_gemma":0.000005226968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003226324,"about_ca_topic_score_gemma":0.00000849044,"domain_scores_codex":[0.9996383,0.00002654395,0.00007885893,0.0001115846,0.00002983302,0.0001148819],"domain_scores_gemma":[0.9992005,0.0004228638,0.00005887018,0.0002326384,0.00005059264,0.00003456122],"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":[0.00002603648,0.0000122368,0.001396867,0.000009498352,0.00001677416,0.000001519256,0.00005236659,0.9293929,0.0003013361,0.0686186,0.000009777225,0.0001621207],"study_design_scores_gemma":[0.0003087516,0.00006151445,0.001481924,0.00007662737,0.00003080548,0.000001390192,0.0001096235,0.9878343,0.005356042,0.00455759,0.00005738505,0.0001240013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5431051,0.000001208907,0.4551068,0.000008237156,0.00001997256,0.00004115229,5.079624e-7,0.00003373601,0.001683306],"genre_scores_gemma":[0.9995571,0.00001175503,0.0003047168,0.00002066681,0.00001948575,2.130048e-7,0.000001267976,0.000009951857,0.00007480226],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4564521,"threshold_uncertainty_score":0.2760614,"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."}}