{"id":"W4396949517","doi":"10.1109/isqed60706.2024.10528676","title":"DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization","year":2024,"lang":"en","type":"article","venue":"","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Memory footprint; Quantization (signal processing); Footprint; Computer science; Reduction (mathematics); Layer (electronics); Artificial intelligence; Algorithm; Mathematics; Geology; Materials science; Nanotechnology","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":[0.000641079,0.001142461,0.0006324831,0.0005215319,0.0003552479,0.0009093085,0.001908657,0.0005803431,0.004064764],"category_scores_gemma":[0.003303667,0.0003649229,0.0004113972,0.0004978269,0.0004188971,0.002002317,0.001290645,0.001619791,0.001081062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008571501,"about_ca_system_score_gemma":0.001288162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007844732,"about_ca_topic_score_gemma":0.01758422,"domain_scores_codex":[0.9995571,0.00004565172,0.00004047458,0.00009540167,0.0002072849,0.00005405576],"domain_scores_gemma":[0.9990803,0.0002533524,0.00008947133,0.0002362804,0.000306035,0.00003457638],"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":[0.0004710202,0.0001661008,0.002034941,0.0002323747,0.0001004315,0.0002577816,0.0001737703,0.1887843,0.04941345,0.006604068,0.01008513,0.7416767],"study_design_scores_gemma":[0.00004268243,0.0001299015,0.0008678261,0.00004106068,0.0000404688,0.0001380391,0.00006512117,0.9450692,0.04346576,0.005261672,0.004854938,0.00002323052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06271044,0.002072265,0.9222744,0.0006048863,0.0003586001,0.0001182003,0.0004346735,0.005954111,0.005472445],"genre_scores_gemma":[0.6264853,0.0008490604,0.362826,0.000524739,0.00009113942,0.0001761886,0.00111372,0.0003440182,0.007589898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007844732,"threshold_uncertainty_score":0.01559818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09691226923567263,"score_gpt":0.3212971273818072,"score_spread":0.2243848581461345,"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."}}