{"id":"W3043802286","doi":"10.1109/isca45697.2020.00075","title":"JPEG-ACT: Accelerating Deep Learning via Transform-based Lossy Compression","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"JPEG; Computer science; Lossy compression; Convolutional neural network; Data compression; Lossless JPEG; Reduction (mathematics); Image compression; Deep learning; Quantization (signal processing); Compression ratio; Artificial intelligence; JPEG 2000; Computer engineering; Computer hardware; Computer vision; Image processing; Image (mathematics)","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":[0.00005276786,0.0001391895,0.0001367395,0.00002602799,0.0003175718,0.0001081328,0.000639673,0.00004358883,0.00008093896],"category_scores_gemma":[0.00001722831,0.0001233445,0.00005640667,0.0004867899,0.00002539111,0.0004782659,0.0001056993,0.000282413,0.0001062816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001810851,"about_ca_system_score_gemma":0.0000186581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004531374,"about_ca_topic_score_gemma":0.000004812288,"domain_scores_codex":[0.9988622,0.00004200274,0.0002209736,0.0004044053,0.0002061641,0.000264232],"domain_scores_gemma":[0.9993268,0.0001366554,0.00007264324,0.0002465368,0.00004317976,0.0001741744],"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":[0.00001517814,0.00005229091,0.0008779578,0.00002798897,0.000007258097,0.00001079085,0.0008592299,0.2657474,0.0472412,0.01072698,0.0003280875,0.6741056],"study_design_scores_gemma":[0.0002446909,0.00006157302,0.0002623589,0.00000781503,0.00000204053,0.00000224997,0.00001144333,0.9672291,0.02264792,0.0005089035,0.008861811,0.0001601439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002479247,0.00004180527,0.9835531,0.007481726,0.00003967879,0.0002157671,1.924688e-7,0.0006694371,0.005519036],"genre_scores_gemma":[0.8062651,0.00000451384,0.1911381,0.002417821,0.00007509374,0.00002585295,0.00000490397,0.00001185154,0.00005676648],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8037859,"threshold_uncertainty_score":0.5029845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03450381076356811,"score_gpt":0.2696955713069403,"score_spread":0.2351917605433722,"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."}}