{"id":"W2786406308","doi":"","title":"Espresso: Efficient Forward Propagation for Binary Deep Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; CUDA; Convolutional neural network; Memory footprint; Parallel computing; Binary number; Deep learning; Artificial neural network; Matrix multiplication; Artificial intelligence; Operating system; Arithmetic","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":[0.0006872264,0.001272044,0.0004609347,0.0007413328,0.0003968635,0.001124572,0.002531779,0.000824743,0.01764983],"category_scores_gemma":[0.002621573,0.0006988714,0.0006905721,0.0008378772,0.0004299179,0.002040342,0.001464563,0.001335,0.006633596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007496604,"about_ca_system_score_gemma":0.001334009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0040186,"about_ca_topic_score_gemma":0.005349453,"domain_scores_codex":[0.9995408,0.00006577196,0.00004502825,0.0000713664,0.0001994382,0.00007751937],"domain_scores_gemma":[0.9994447,0.0002024449,0.00005956333,0.0001128092,0.0001472289,0.0000332035],"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":[0.001285438,0.0003352942,0.002000808,0.001369281,0.0001987085,0.0004260538,0.0002327191,0.1110218,0.03841546,0.04433609,0.1607168,0.6396616],"study_design_scores_gemma":[0.0001967663,0.0001320174,0.0005626509,0.0001075114,0.0000389801,0.0001925562,0.00003405776,0.8854188,0.04559506,0.02052299,0.04715153,0.00004708871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02100972,0.001000613,0.8614811,0.0003201776,0.0003407892,0.0001544896,0.002409518,0.09921192,0.01407167],"genre_scores_gemma":[0.2020267,0.000817914,0.7535855,0.000549641,0.0001142572,0.0005585788,0.01011372,0.01026825,0.02196538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01764983,"threshold_uncertainty_score":0.05904454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0384290167936386,"score_gpt":0.3438460892558937,"score_spread":0.3054170724622551,"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."}}