{"id":"W2198190323","doi":"10.48550/arxiv.1510.03009","title":"Neural Networks with Few Multiplications","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"MNIST database; Computer science; Artificial neural network; Multiplication (music); Gradient descent; Computation; Point (geometry); Artificial intelligence; Layer (electronics); Stochastic gradient descent; Binary number; Sign (mathematics); Deep neural networks; Algorithm; Training (meteorology); Backpropagation; Arithmetic; Pattern recognition (psychology); Mathematics","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":[0.0008736902,0.001493909,0.0008961291,0.0004949079,0.0007516641,0.001642929,0.001891284,0.001146877,0.01876613],"category_scores_gemma":[0.005618211,0.0008527283,0.0006700564,0.0008535527,0.001164655,0.004173709,0.001808284,0.003456779,0.01075794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007211706,"about_ca_system_score_gemma":0.00111579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00273362,"about_ca_topic_score_gemma":0.006356462,"domain_scores_codex":[0.9991736,0.0001613056,0.00006265131,0.0002149409,0.0003083858,0.0000790715],"domain_scores_gemma":[0.9988227,0.0004256746,0.00007539235,0.0004631724,0.0001699547,0.00004307862],"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":[0.0005101883,0.0001353229,0.0009082562,0.0005536846,0.0001399575,0.0002714896,0.0001526975,0.1346228,0.01313951,0.1168717,0.03528164,0.6974128],"study_design_scores_gemma":[0.0001035662,0.0002034937,0.0004420582,0.0001153867,0.00006102594,0.0003529319,0.00004075856,0.7896592,0.01173628,0.1617806,0.03545189,0.00005280418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01796504,0.00249787,0.9530818,0.001592759,0.0007730884,0.0001318494,0.0004837467,0.005750996,0.0177228],"genre_scores_gemma":[0.3330651,0.00202546,0.6181661,0.001392132,0.0005813978,0.000632015,0.0012223,0.0008487879,0.04206667],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01876613,"threshold_uncertainty_score":0.06277895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08012054912875996,"score_gpt":0.2036987402104443,"score_spread":0.1235781910816844,"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."}}