{"id":"W2473751517","doi":"10.5555/2959355.2959416","title":"Accelerating embedded deep learning using DeepX: demonstration abstract","year":2016,"lang":"en","type":"article","venue":"Information Processing in Sensor Networks","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Deep learning; Computer science; Convolutional neural network; Artificial intelligence; Inference; Artificial neural network; Deep neural networks; Software; Mobile device; Computer architecture; Resource (disambiguation); Embedded system; Machine learning; Computer engineering; Operating system; Computer network","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":[0.0005855101,0.0005865512,0.0002770287,0.0001744299,0.0001829037,0.0004123271,0.001202202,0.0005232912,0.008699649],"category_scores_gemma":[0.0009761945,0.000204669,0.0002021092,0.0002639868,0.0003520147,0.0007969881,0.0007318928,0.001242581,0.001332421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003942812,"about_ca_system_score_gemma":0.0006307356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004418351,"about_ca_topic_score_gemma":0.003700818,"domain_scores_codex":[0.9998015,0.00002767909,0.000008692469,0.00002673626,0.00009457455,0.00004079453],"domain_scores_gemma":[0.9995891,0.0001220126,0.0000220404,0.00006026358,0.0001260924,0.0000805151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003356841,0.001410613,0.007251534,0.0008189894,0.0002513121,0.001507901,0.0004120294,0.2864585,0.1753359,0.03652461,0.1880258,0.298646],"study_design_scores_gemma":[0.0003301914,0.0005210376,0.001215923,0.00003417514,0.00001622608,0.0001058968,0.00004141459,0.9082207,0.0623903,0.005372868,0.02172784,0.00002338869],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4990113,0.001668706,0.4016564,0.004674688,0.001629176,0.0003692685,0.002748214,0.0467345,0.04150761],"genre_scores_gemma":[0.8274736,0.0004410799,0.1554967,0.0004668246,0.00006001842,0.0001910471,0.001304003,0.0007018592,0.01386493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008699649,"threshold_uncertainty_score":0.02910322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02504612971637403,"score_gpt":0.2743456450988635,"score_spread":0.2492995153824895,"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."}}