{"id":"W4288574626","doi":"10.48550/arxiv.1902.06468","title":"Beyond the Memory Wall: A Case for Memory-centric HPC System for Deep\\n Learning","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Ferroelectric and Negative Capacitance Devices","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Bottleneck; Computer science; Speedup; Memory map; Memory management; Flat memory model; Parallel computing; Computer architecture; Interconnection; Auxiliary memory; Interface (matter); Memory model; Shared memory; Registered memory; Deep learning; Interleaved memory; Semiconductor memory; Embedded system; Computer hardware; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001053112,0.001135111,0.001282005,0.0005502673,0.001147852,0.0001992401,0.001361771,0.0008401431,0.00007668964],"category_scores_gemma":[0.000259416,0.001127221,0.001153632,0.001220761,0.0002248684,0.0004549926,0.0003712107,0.001601572,0.0001600851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00167946,"about_ca_system_score_gemma":0.0002365309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001464454,"about_ca_topic_score_gemma":0.0001285989,"domain_scores_codex":[0.9954433,0.0003502639,0.0007240828,0.001846024,0.0001813514,0.001454968],"domain_scores_gemma":[0.9944304,0.002454533,0.0007390172,0.001288889,0.0007494137,0.0003377238],"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":[0.0005752004,0.0000785875,0.0002184864,0.00551135,0.001370173,0.0009771326,0.002298713,0.9669937,0.0001332251,0.01881417,0.0004877818,0.002541425],"study_design_scores_gemma":[0.003293692,0.0003226818,0.00003239593,0.0004319219,0.001626752,0.0002799935,0.01381192,0.9737135,0.0009179587,0.00109839,0.003131135,0.001339668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4450084,0.003655992,0.5327474,0.00009006042,0.00354484,0.006699921,0.0001884907,0.0005572213,0.007507698],"genre_scores_gemma":[0.991061,0.0008388658,0.0003318841,0.00007698599,0.0004596738,0.00006233888,0.00007906394,0.000215548,0.006874637],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5460526,"threshold_uncertainty_score":0.9991178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03609979902030499,"score_gpt":0.1765480189848058,"score_spread":0.1404482199645009,"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."}}