{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001734066,0.0001756879,0.0001307708,0.0001889691,0.0005511699,0.0002819451,0.0009481361,0.00006542169,0.00008407126],"category_scores_gemma":[0.0003060662,0.0001764065,0.00009498589,0.0003950857,0.0001415821,0.0003862807,0.0002123028,0.0002686082,0.00007888459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007901042,"about_ca_system_score_gemma":0.00003617492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008812057,"about_ca_topic_score_gemma":0.000009404709,"domain_scores_codex":[0.9982457,0.00008964004,0.0003332213,0.0006359578,0.0003863193,0.0003091846],"domain_scores_gemma":[0.9980044,0.0003989808,0.0002519253,0.0004534553,0.0007881204,0.0001030596],"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":[0.00005414596,0.0001000932,0.0004875465,0.000002953084,0.00003063111,0.000002366806,0.0005635658,0.6278361,0.001577246,0.3325568,0.0004935177,0.03629505],"study_design_scores_gemma":[0.0003540498,0.0002126843,0.001860763,0.00001668295,0.000007295438,0.000008115101,0.00006966018,0.9901053,0.0005996698,0.004498456,0.002087211,0.0001801321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01304596,0.00001197254,0.9729536,0.005693659,0.0008672475,0.0006108079,0.000005161838,0.0003299905,0.006481602],"genre_scores_gemma":[0.980784,0.000008944166,0.01683557,0.0002918633,0.0004905313,0.0004694552,0.00008844581,0.00001969781,0.00101149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.967738,"threshold_uncertainty_score":0.7193646,"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."}}