{"id":"W2912563840","doi":"10.1109/icip.2019.8803110","title":"Multi-Task Learning with Compressible Features for Collaborative Intelligence","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cloud computing; Computer science; Task (project management); Artificial neural network; Artificial intelligence; Feature (linguistics); Deep learning; Distributed computing; Reduction (mathematics); Compressibility; Mobile device; Engineering; Operating system; Systems engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002318709,0.0003874825,0.0004753354,0.0001531025,0.0001539869,0.0004457307,0.00151508,0.0002387892,0.000006984566],"category_scores_gemma":[0.0001254634,0.000287431,0.0001000158,0.0003842541,0.00008499362,0.0004859557,0.001407019,0.0008329435,0.00001684177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006818026,"about_ca_system_score_gemma":0.0002628578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002853968,"about_ca_topic_score_gemma":0.00001387282,"domain_scores_codex":[0.9980271,0.00007868374,0.0002773453,0.0009705919,0.0002808063,0.0003654726],"domain_scores_gemma":[0.997675,0.0003145191,0.0003220944,0.0008858438,0.0007184903,0.00008404935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008201344,0.0008566125,0.002037818,0.002584817,0.0008135642,0.0001011425,0.01078046,0.1892737,0.009480134,0.08266512,0.01862792,0.6819586],"study_design_scores_gemma":[0.0008741386,0.001820679,0.0005413985,0.001295062,0.00005839998,0.0000237871,0.0006543573,0.2465249,0.6595732,0.01895512,0.06746247,0.002216457],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004331912,0.001211163,0.9934288,0.0001913638,0.0002344384,0.001644846,0.00001827638,0.0008144624,0.002413292],"genre_scores_gemma":[0.06693053,0.0003311074,0.9253039,0.0002193669,0.00005242668,0.0002322297,0.00002999925,0.00003311392,0.006867362],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6797421,"threshold_uncertainty_score":0.9999578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03669897160282987,"score_gpt":0.331557469142168,"score_spread":0.2948584975393382,"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."}}