{"id":"W2942114164","doi":"10.48550/arxiv.1610.06920","title":"Bit-pragmatic Deep Neural Network Computing","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Ferroelectric and Negative Capacitance Devices","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Computation; Exploit; Latency (audio); Efficient energy use; Context (archaeology); Representation (politics); Product (mathematics); Convolutional neural network; Parallel computing; Arithmetic; Algorithm; Mathematics; Artificial intelligence","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":[0.00007845293,0.0001448682,0.0001513163,0.00006374723,0.00009298328,0.00001306101,0.0001996446,0.00005631726,0.00008726511],"category_scores_gemma":[0.00002010093,0.0001227676,0.00006407317,0.0005113426,0.00005930503,0.0002401185,0.0000294166,0.00009862476,0.0001635972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009056568,"about_ca_system_score_gemma":0.000005611082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003034361,"about_ca_topic_score_gemma":0.00001843897,"domain_scores_codex":[0.999256,0.00003887869,0.0001040868,0.0002107857,0.00003619425,0.00035407],"domain_scores_gemma":[0.9994547,0.0002002319,0.00003589368,0.0001844651,0.0000370719,0.00008765276],"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":[0.00003142231,0.00002140732,0.01680996,0.00007004631,0.0001382655,0.0001727508,0.0002094914,0.9176725,0.001442373,0.0503024,0.001643398,0.01148595],"study_design_scores_gemma":[0.0005317584,0.00003711576,0.003891267,0.00006289614,0.00003029259,0.00000569329,0.00008105791,0.989895,0.0003050756,0.004253221,0.0006117482,0.0002948002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8158993,0.0001822753,0.1784908,0.00002574162,0.0002671381,0.00007596745,0.000001630976,0.0003450219,0.004712175],"genre_scores_gemma":[0.9993153,0.00006742112,0.000136333,0.00005561961,0.0001208814,1.547501e-7,0.000001160425,0.00002001167,0.0002830686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1834161,"threshold_uncertainty_score":0.5006319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02597229559431874,"score_gpt":0.1507320751719576,"score_spread":0.1247597795776388,"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."}}