{"id":"W4387250519","doi":"10.1109/asap57973.2023.00024","title":"Efficient 1D Grouped Convolution for PyTorch a Case Study: Fast On-Device Fine-Tuning for SqueezeBERT","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Convolution (computer science); Locality; Edge device; Enhanced Data Rates for GSM Evolution; Inference; Memory management; Parallel computing; Reduction (mathematics); Algorithm; Edge computing; Base (topology); Computational science; Computer engineering; Theoretical computer science; Artificial intelligence; Computer hardware; Mathematics; Semiconductor memory; Operating system","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":[0.0005614913,0.000945751,0.0005972824,0.0003123796,0.000501127,0.0009491859,0.001891786,0.0009677566,0.00606412],"category_scores_gemma":[0.00206839,0.0003596439,0.0004939142,0.0004198494,0.0006061086,0.001986341,0.001113142,0.001351326,0.0008946118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001147179,"about_ca_system_score_gemma":0.001239276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009718765,"about_ca_topic_score_gemma":0.01512342,"domain_scores_codex":[0.9996668,0.00004796791,0.00001611171,0.00009024915,0.00009749694,0.00008136026],"domain_scores_gemma":[0.9994069,0.0002544946,0.00002796045,0.0001666062,0.00009620949,0.00004776411],"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":[0.001787518,0.0003194868,0.006399217,0.0005302752,0.0002318025,0.0015662,0.0003296302,0.5977682,0.06787924,0.02297198,0.0201964,0.28002],"study_design_scores_gemma":[0.00002938634,0.00009499389,0.000414832,0.00001134312,0.00001447664,0.0001189357,0.00002838628,0.9676206,0.02552148,0.003133769,0.002996538,0.0000152778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3854878,0.001446355,0.5612308,0.001175914,0.0003590008,0.0001588813,0.0007570092,0.03370173,0.01568249],"genre_scores_gemma":[0.8209482,0.0001605174,0.1717104,0.000246948,0.00002012835,0.00006371253,0.0004479961,0.0006631323,0.005738848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009718765,"threshold_uncertainty_score":0.0202865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06023549413193496,"score_gpt":0.3403309898159317,"score_spread":0.2800954956839968,"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."}}