{"id":"W3043884287","doi":"10.48550/arxiv.2007.10451","title":"HPIPE: Heterogeneous Layer-Pipelined and Sparse-Aware CNN Inference for FPGAs","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Stratix; Field-programmable gate array; Compiler; Convolutional neural network; Parallel computing; Throughput; Computer architecture; Layer (electronics); Lookup table; Embedded system; Computer hardware; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007570032,0.0003686455,0.0003766374,0.000111136,0.0002197973,0.0001197148,0.001638168,0.0002292343,0.000006630847],"category_scores_gemma":[0.00005367175,0.0004412319,0.0001576387,0.0004665218,0.0001108831,0.0002603086,0.002366286,0.0004344512,0.00004289693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009498055,"about_ca_system_score_gemma":0.0001286848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002112023,"about_ca_topic_score_gemma":0.00003785927,"domain_scores_codex":[0.997716,0.00006224251,0.0002315001,0.00152149,0.00007934496,0.0003894639],"domain_scores_gemma":[0.997814,0.0003016047,0.0002664278,0.001143504,0.0001870309,0.0002874388],"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":[0.00007167458,0.00009005049,0.0007286621,0.0002137045,0.0001038278,0.0002198799,0.0002271961,0.7938918,0.0002939946,0.1964745,0.0009724579,0.006712253],"study_design_scores_gemma":[0.0003986857,0.00006143747,0.0001204758,0.00004714097,0.00005040464,0.000007270285,0.00001045662,0.8806662,0.000594424,0.1146766,0.002897872,0.0004689733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03554778,0.00009133003,0.9619783,0.0007336196,0.0002299783,0.0007877332,0.00005354527,0.0004102932,0.000167425],"genre_scores_gemma":[0.9839976,0.0003177796,0.01469924,0.0003922318,0.0001270231,0.00001295354,0.0000363805,0.00002753755,0.0003892114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9484499,"threshold_uncertainty_score":0.999804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1361301914331658,"score_gpt":0.2355188951467013,"score_spread":0.0993887037135355,"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."}}