{"id":"W4292632476","doi":"10.1007/978-3-030-98347-5_19","title":"Efficient Approximate DNN Accelerators for Edge Devices: An Experimental Study","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"GaN-based semiconductor devices and materials","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Inference; Multiplier (economics); Deep neural networks; Computation; Computer science; Edge device; Enhanced Data Rates for GSM Evolution; Function (biology); Artificial neural network; Algorithm; Computer engineering; Artificial intelligence","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":[0.0005803624,0.0004840626,0.0005217076,0.0002478983,0.0006159266,0.00140855,0.001336502,0.0006185418,0.01709898],"category_scores_gemma":[0.001074865,0.0002325181,0.0002527589,0.0006466432,0.0004083932,0.001637297,0.0004617577,0.0008458847,0.00184703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001570568,"about_ca_system_score_gemma":0.0007488996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00223956,"about_ca_topic_score_gemma":0.003499166,"domain_scores_codex":[0.9996326,0.00006622988,0.00001078889,0.00004971661,0.0001842562,0.00005637451],"domain_scores_gemma":[0.9992987,0.0003496757,0.00007213702,0.0001030979,0.0001259438,0.00005038022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.007003059,0.001743736,0.005428634,0.001198355,0.0004207477,0.0005474705,0.0004239029,0.1162904,0.4044006,0.1775433,0.03668926,0.2483106],"study_design_scores_gemma":[0.0002831794,0.001115269,0.00204172,0.0000874564,0.0001320851,0.0005312906,0.0002235669,0.7118556,0.2405737,0.01434275,0.02875225,0.00006106128],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5247163,0.004276503,0.268737,0.001073034,0.000437068,0.0003508914,0.001284947,0.005229568,0.1938946],"genre_scores_gemma":[0.872813,0.0007477424,0.09275364,0.0002586668,0.0000526444,0.0001080308,0.0007222935,0.0003176469,0.03222639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01709898,"threshold_uncertainty_score":0.05720174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04179005161943671,"score_gpt":0.2896277489400447,"score_spread":0.247837697320608,"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."}}