{"id":"W2999003874","doi":"10.1109/syscon47679.2020.9275895","title":"Machine Learning-Based Self-Compensating Approximate Computing","year":2020,"lang":"en","type":"preprint","venue":"2020 IEEE International Systems Conference (SysCon)","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Overhead (engineering); Compensation (psychology); Process (computing); Energy (signal processing); Efficient energy use; Multiplication (music); Power (physics); Range (aeronautics); Approximation error; Computer engineering; Computer hardware; Algorithm","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":[0.0002389045,0.0003243301,0.0004087228,0.0002830513,0.0002282117,0.0004563259,0.0009553032,0.0003298347,0.00143901],"category_scores_gemma":[0.0008830745,0.0001735726,0.0002858985,0.0004207426,0.0002897498,0.0007439184,0.000438639,0.0004375423,0.0004402593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000402925,"about_ca_system_score_gemma":0.0005324447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001104823,"about_ca_topic_score_gemma":0.001657538,"domain_scores_codex":[0.9997789,0.00002725564,0.00001389464,0.00004147627,0.0001119505,0.00002651918],"domain_scores_gemma":[0.999658,0.00007559628,0.00005185113,0.00009630371,0.0001045711,0.00001364377],"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":[0.0003730318,0.0001455099,0.002128036,0.0002017604,0.0000933877,0.000124257,0.0001224071,0.4340173,0.08059634,0.02240548,0.003133248,0.4566593],"study_design_scores_gemma":[0.000004748457,0.00005039889,0.000201638,0.000003846871,0.000007102683,0.00003763512,0.000003817363,0.9845545,0.01203315,0.001663262,0.001435159,0.000004818182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03368739,0.0002589119,0.9626479,0.00006168187,0.00004341261,0.00002274445,0.00003412959,0.001273753,0.001970143],"genre_scores_gemma":[0.6882726,0.0002094412,0.3075498,0.00009366916,0.0000395069,0.00006965025,0.0001587982,0.00008131423,0.003525201],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00143901,"threshold_uncertainty_score":0.004813969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04035836263325595,"score_gpt":0.2684552409130203,"score_spread":0.2280968782797644,"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."}}