{"id":"W4417169891","doi":"10.1109/icecs66544.2025.11270647","title":"Systematic Framework Leveraging Early Assessment of DNN Reliability for Efficient and Reliable FPGA-Based Inference Deployment","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Inference; Software deployment; Python (programming language); Field-programmable gate array; Artificial neural network; Software; Reliability (semiconductor); Scheduling (production processes); Fault tolerance","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":[0.002136075,0.001720394,0.0005745405,0.001201617,0.0004199877,0.001209807,0.002173733,0.0007098879,0.002344272],"category_scores_gemma":[0.008434996,0.0005658015,0.0005851698,0.0003490314,0.000675395,0.002107629,0.001874724,0.001247124,0.0007597078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001120366,"about_ca_system_score_gemma":0.002909452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005094223,"about_ca_topic_score_gemma":0.008092398,"domain_scores_codex":[0.9985678,0.0003209584,0.0001094088,0.0002651782,0.0005670699,0.0001695571],"domain_scores_gemma":[0.9969272,0.0009839006,0.000328871,0.0007468237,0.0008948203,0.0001185028],"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":[0.000668826,0.0002358322,0.01100721,0.000534379,0.0002077829,0.0004850163,0.0002087842,0.5525978,0.06863163,0.01197697,0.008038322,0.3454075],"study_design_scores_gemma":[0.00002302369,0.000127323,0.0009275746,0.00003708675,0.00003997727,0.00009269454,0.00002861338,0.9551696,0.03697458,0.004423093,0.002128312,0.00002820784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06379599,0.0007696485,0.9121539,0.000285064,0.0001127816,0.0002126607,0.0003014081,0.01921491,0.003153601],"genre_scores_gemma":[0.6470146,0.0003523782,0.3486038,0.0002224062,0.00005373563,0.0002337488,0.0006880661,0.001216581,0.001614706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005094223,"threshold_uncertainty_score":0.01129681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02121898758092157,"score_gpt":0.326227407700956,"score_spread":0.3050084201200344,"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."}}