{"id":"W2996273387","doi":"","title":"FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Convolutional neural network; Computer science; Convolution (computer science); Artificial intelligence; Pattern recognition (psychology); Quantization (signal processing); Deep learning; Algorithm; Image compression; Filter (signal processing); Artificial neural network; Computer vision; Image processing; Image (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":[0.0003358994,0.0008387403,0.0004900152,0.0006371688,0.000229792,0.000501224,0.001109043,0.0005337964,0.002786912],"category_scores_gemma":[0.001227215,0.0002383446,0.0004254088,0.0006798536,0.0004443232,0.001721058,0.0007520101,0.0007829205,0.000681513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005704864,"about_ca_system_score_gemma":0.0007202406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003647986,"about_ca_topic_score_gemma":0.005612269,"domain_scores_codex":[0.9997876,0.00002019383,0.00001736562,0.00004348065,0.0001069586,0.00002438185],"domain_scores_gemma":[0.9997174,0.00005768449,0.00003446229,0.0001038204,0.00007086914,0.00001569816],"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":[0.0003440585,0.0001359263,0.001434367,0.0001594678,0.0001067611,0.0002917587,0.00009774286,0.2333873,0.05669829,0.02181092,0.01003286,0.6755005],"study_design_scores_gemma":[0.00002632258,0.000156548,0.0005288831,0.00001983914,0.00002377171,0.000208145,0.00001950312,0.9401394,0.04167873,0.008594966,0.00858683,0.00001703089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05049266,0.0007435141,0.9406877,0.0002097402,0.000209883,0.00009440937,0.0004722537,0.003872594,0.003217176],"genre_scores_gemma":[0.5265967,0.000805215,0.4598906,0.0003152687,0.0001669113,0.0002079075,0.002225253,0.0003401077,0.009451912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003647986,"threshold_uncertainty_score":0.00932312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04455970726502237,"score_gpt":0.1810260813521052,"score_spread":0.1364663740870828,"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."}}