{"id":"W4312868944","doi":"10.1109/iscas48785.2022.9937567","title":"Efficient Fine-Tuning of BERT Models on the Edge","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Adaptability; Software deployment; Edge device; Fine-tuning; Computation; Inference; Distributed computing; Resource (disambiguation); Metric (unit); Resource allocation; Artificial intelligence; 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":[0.0008302468,0.001476194,0.0008988065,0.0003952591,0.000399787,0.001076505,0.002513613,0.001123294,0.004521324],"category_scores_gemma":[0.004001956,0.0007217037,0.000722668,0.0003771405,0.000767386,0.003014935,0.001525105,0.002533393,0.001812203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00089318,"about_ca_system_score_gemma":0.001139692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006600625,"about_ca_topic_score_gemma":0.01351085,"domain_scores_codex":[0.9996238,0.00007710831,0.00001940187,0.0001114136,0.00008253429,0.0000856927],"domain_scores_gemma":[0.9991586,0.0003179294,0.00005218305,0.0002791332,0.0001277931,0.00006438894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004259767,0.0001924834,0.002789169,0.0001286749,0.00007734719,0.0001765516,0.0001082677,0.8380496,0.0104278,0.005909013,0.01425277,0.1274624],"study_design_scores_gemma":[0.00001219678,0.00003239512,0.000167735,0.000006867093,0.000006426616,0.00002130078,0.00001533655,0.9935195,0.002124454,0.002939222,0.00114736,0.000007281393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.235694,0.001486178,0.7104589,0.001495649,0.0004401343,0.0001836898,0.001063863,0.03148063,0.01769695],"genre_scores_gemma":[0.8885105,0.0002600066,0.101767,0.0007315378,0.00006042368,0.0001470782,0.001556826,0.001025616,0.005941057],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006600625,"threshold_uncertainty_score":0.01512527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03886087501171164,"score_gpt":0.2612023358593475,"score_spread":0.2223414608476358,"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."}}