{"id":"W2297325673","doi":"","title":"DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices","year":2016,"lang":"en","type":"article","venue":"Open MIND","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":300,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Inference; Mobile device; Bottleneck; Overhead (engineering); Machine learning; Mobile processor; Field (mathematics); Computer architecture; Embedded system; Distributed computing; Computer engineering; Mobile technology; Mobile Web; Operating system","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003482647,0.000165752,0.0001889398,0.00006681884,0.0002974184,0.0004926837,0.001560873,0.00007351702,0.000136499],"category_scores_gemma":[0.0002069766,0.000116773,0.00005783668,0.0001781069,0.00002730103,0.000788443,0.0007098262,0.0001084291,0.0007908238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004615876,"about_ca_system_score_gemma":0.0001032754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005017047,"about_ca_topic_score_gemma":0.000008316197,"domain_scores_codex":[0.9986444,0.00004786636,0.0002148867,0.0005242425,0.0001653424,0.00040327],"domain_scores_gemma":[0.9986917,0.0005673803,0.0001246288,0.0003858886,0.0001231444,0.0001072002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001713587,0.00004871131,0.003618818,0.000007187521,0.00001227416,0.000005886178,0.001190393,0.00004968163,0.0005676991,0.00006866199,0.0003987564,0.9940148],"study_design_scores_gemma":[0.002837004,0.001782659,0.007810201,0.0009037756,0.00002112623,0.00001549922,0.0001525702,0.01522422,0.04391081,0.001089826,0.9247681,0.001484158],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.549461,0.00005137269,0.4455199,0.0001479689,0.001954216,0.0005619086,7.445578e-7,0.00002614557,0.002276729],"genre_scores_gemma":[0.9045849,0.000002362537,0.09352853,0.0001742605,0.000409685,0.00007634575,0.000002068433,0.00001751951,0.001204313],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9925306,"threshold_uncertainty_score":0.9999872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.036033239521602,"score_gpt":0.3149476944980685,"score_spread":0.2789144549764665,"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."}}