{"id":"W4297127979","doi":"10.48550/arxiv.1802.00844","title":"Intriguing Properties of Randomly Weighted Networks: Generalizing While\\n Learning Next to Nothing","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Generalization; Computer science; Artificial intelligence; Deep learning; Property (philosophy); Artificial neural network; Set (abstract data type); Convolutional neural network; Layer (electronics); Backpropagation; Machine learning; 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":[0.002563994,0.0009102759,0.000583879,0.0007021343,0.0006477627,0.001334592,0.00151833,0.001763277,0.002148698],"category_scores_gemma":[0.01604602,0.0005268119,0.0006982473,0.0005904585,0.003073667,0.005382497,0.001984265,0.003693804,0.0004229088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007779993,"about_ca_system_score_gemma":0.0005691609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001868468,"about_ca_topic_score_gemma":0.002311481,"domain_scores_codex":[0.9988071,0.0004218015,0.00004935238,0.0004026518,0.0002145813,0.000104608],"domain_scores_gemma":[0.9945441,0.002909888,0.0005595348,0.001448744,0.0003623137,0.000175421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000164285,0.00008519897,0.003386955,0.0002087714,0.0001376293,0.0003578411,0.000403515,0.2309717,0.01063593,0.6589339,0.005861017,0.08885317],"study_design_scores_gemma":[0.0000151721,0.00006519802,0.0006211372,0.00002785815,0.00001955888,0.0001355548,0.00003329354,0.3776064,0.001846993,0.6162779,0.003333515,0.00001749294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08614473,0.0009877803,0.8902169,0.004053873,0.0002184279,0.00006721997,0.000220656,0.0009176768,0.01717267],"genre_scores_gemma":[0.8831596,0.001860937,0.1028758,0.00177666,0.0005168166,0.0002345774,0.0005645055,0.0005864289,0.008424575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002563994,"threshold_uncertainty_score":0.01355988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08361096156503091,"score_gpt":0.1862872091393258,"score_spread":0.1026762475742949,"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."}}