{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003253179,0.0001277485,0.0001506933,0.00003167251,0.0001176336,0.00001448825,0.0008569798,0.00005999085,0.00003430139],"category_scores_gemma":[0.000007934955,0.0001403245,0.00007419752,0.0006645969,0.0001142922,0.0004350525,0.0003967603,0.0001727644,0.0000179449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000271063,"about_ca_system_score_gemma":0.00001222926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005685274,"about_ca_topic_score_gemma":0.000002283006,"domain_scores_codex":[0.9990366,0.00006193932,0.0001444063,0.0004630116,0.00006990005,0.0002242197],"domain_scores_gemma":[0.9991437,0.0001302729,0.0001283901,0.000358468,0.00006720051,0.0001719304],"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":[0.00004013174,0.0000535696,0.002954068,0.000007621613,0.00001627289,0.00002500968,0.00004844449,0.9247537,0.001249847,0.06111436,0.008012496,0.001724529],"study_design_scores_gemma":[0.0003270803,0.00004786917,0.0007152183,0.000005542828,0.000008051399,0.000002054371,0.000008461796,0.9950983,0.0002691854,0.001520044,0.001857874,0.0001403451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02819071,0.0001619296,0.9703444,0.0004769005,0.00007621473,0.0001316382,0.000008638105,0.0001267256,0.0004828631],"genre_scores_gemma":[0.9972299,0.0000412421,0.001790382,0.0007128991,0.00005381849,6.282696e-7,0.00002080218,0.000007948998,0.0001423226],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9690393,"threshold_uncertainty_score":0.5722267,"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."}}