{"id":"W2904327456","doi":"10.1109/micro.2018.00020","title":"Diffy: a Déjà vu-Free Differential Deep Neural Network Accelerator","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Computer science; Bandwidth (computing); Chip; Convolution (computer science); Computation; Artificial neural network; Energy (signal processing); Computer hardware; Computational science; Computer engineering; Artificial intelligence; Algorithm; Telecommunications; 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":[0.0000525593,0.0002212347,0.0001912062,0.0000432979,0.000400401,0.0002119257,0.002244245,0.00006973815,0.000232993],"category_scores_gemma":[0.00002147956,0.0001852284,0.0000814325,0.0006954179,0.0001365537,0.0005173226,0.001196613,0.0001762016,0.0002733691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003042035,"about_ca_system_score_gemma":0.00001704656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006738642,"about_ca_topic_score_gemma":0.00009271723,"domain_scores_codex":[0.998198,0.00004938913,0.000268106,0.0006019712,0.0002682157,0.0006143451],"domain_scores_gemma":[0.9979132,0.0001120014,0.00009459314,0.001574091,0.0001017979,0.0002042771],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005226921,0.0002853836,0.002072725,0.00001075758,0.00006464477,0.00002154608,0.0004130617,0.00183996,0.007496858,0.6288453,0.1105264,0.2483711],"study_design_scores_gemma":[0.001113769,0.0002977884,0.01334481,0.00001000501,0.0000187027,0.00004227142,0.000008876124,0.8700486,0.004354539,0.07957539,0.03037675,0.0008084909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03362112,0.0000538036,0.9582126,0.002083717,0.0008630275,0.0002810352,0.000001412703,0.0006943256,0.004188942],"genre_scores_gemma":[0.9096796,0.000007634771,0.08552084,0.001891115,0.002081464,0.0000729607,0.000003474184,0.00002233443,0.0007205709],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8760585,"threshold_uncertainty_score":0.7553397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02030057917802687,"score_gpt":0.2617721245926274,"score_spread":0.2414715454146006,"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."}}