{"id":"W4311681113","doi":"10.22215/etd/2022-15289","title":"Optimization of Convolutional Neural Networks for Constrained Devices through Binarization","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Convolutional neural network; Quantization (signal processing); Artificial intelligence; Convolution (computer science); Artificial neural network; Binary number; Feature extraction; Deep learning; Pattern recognition (psychology); Constrained optimization problem; Feature (linguistics); Algorithm; Optimization problem; Mathematics","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":[0.0003926456,0.001026671,0.0007369712,0.0003781141,0.0003442004,0.0008367335,0.0007219779,0.0007305145,0.00495871],"category_scores_gemma":[0.0008968735,0.000496105,0.0005434119,0.000552346,0.0005577801,0.001040475,0.0008669721,0.0009421105,0.0007550612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001152195,"about_ca_system_score_gemma":0.001242968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003952492,"about_ca_topic_score_gemma":0.006750547,"domain_scores_codex":[0.9997974,0.0000329568,0.000008566234,0.0000483605,0.00007841647,0.00003433884],"domain_scores_gemma":[0.9998271,0.00008333623,0.00001985608,0.00002216093,0.0000367578,0.00001078722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004465683,0.00002884945,0.0002108264,0.00007360891,0.00002933723,0.00004643066,0.00002688031,0.9141091,0.00548572,0.01874753,0.001952424,0.05924474],"study_design_scores_gemma":[0.000003029793,0.000007507103,0.00003752646,0.000004861046,0.000002839788,0.00001000357,0.000003760493,0.9956482,0.001019344,0.002294771,0.0009655786,0.000002477143],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01469059,0.0004817861,0.9763557,0.0001612073,0.00004718682,0.00005026389,0.00007188642,0.0006121965,0.007529101],"genre_scores_gemma":[0.453008,0.0008022339,0.5284837,0.0001911349,0.00004124078,0.0002778606,0.0003475288,0.0006255081,0.01622277],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00495871,"threshold_uncertainty_score":0.01658857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01906145602148955,"score_gpt":0.2925302118463711,"score_spread":0.2734687558248815,"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."}}