{"id":"W2901612323","doi":"10.1109/nocarc.2018.8541207","title":"Value-Based Deep Learning Hardware Acceleration","year":2018,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Exploit; Computer science; Deep learning; Retraining; Hardware acceleration; Acceleration; Efficient energy use; Energy (signal processing); Artificial neural network; Computer engineering; Artificial intelligence; Computer architecture; Embedded system; Field-programmable gate array","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":[0.000198889,0.00007346238,0.00006526566,0.0000796149,0.0002387066,0.0002073158,0.0003985584,0.00004067195,0.0000636413],"category_scores_gemma":[0.00004842922,0.00006670166,0.00002894323,0.0002547555,0.00002566439,0.000246896,0.00008476669,0.00007511145,0.0001186829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002003781,"about_ca_system_score_gemma":0.00003104614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001170992,"about_ca_topic_score_gemma":0.000002505219,"domain_scores_codex":[0.9993044,0.00006641338,0.000118319,0.0002237749,0.0001424818,0.0001445731],"domain_scores_gemma":[0.9994826,0.00003568147,0.00004860727,0.000239963,0.0001507148,0.00004243499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001846642,0.0001745206,0.004645767,0.00002338908,0.00002665709,0.000009192024,0.001660239,0.2644377,0.00264889,0.2963941,0.01831147,0.4116495],"study_design_scores_gemma":[0.00009852473,0.0000961687,0.0003122925,0.00000600977,8.723669e-7,0.000001211886,0.000003012067,0.974367,0.01605795,0.0007360874,0.00822346,0.00009738309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006079718,0.00001334168,0.9714,0.000434622,0.0001114402,0.00005863959,4.721835e-8,0.001399413,0.02597453],"genre_scores_gemma":[0.5021661,0.000001502762,0.4964766,0.0006295228,0.00007008572,0.000003523813,0.000002538352,0.000004043554,0.0006461417],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7099293,"threshold_uncertainty_score":0.2720015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02011273078662947,"score_gpt":0.2688489871341832,"score_spread":0.2487362563475538,"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."}}