{"id":"W2786262858","doi":"10.1109/crv.2019.00010","title":"Intriguing Properties of Randomly Weighted Networks: Generalizing While Learning Next to Nothing","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":4,"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); Machine learning; Backpropagation; 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":[0.003081242,0.0009737752,0.000732465,0.0007551436,0.0005897946,0.001223763,0.00160761,0.001834938,0.001696125],"category_scores_gemma":[0.01764876,0.0005931137,0.0007940162,0.0006669072,0.003097888,0.005736928,0.002100228,0.003360706,0.000389258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006685679,"about_ca_system_score_gemma":0.000485382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001233332,"about_ca_topic_score_gemma":0.001393828,"domain_scores_codex":[0.9986325,0.0005358817,0.00006528499,0.0004224245,0.0002335784,0.0001103287],"domain_scores_gemma":[0.9935318,0.00354619,0.0007219198,0.00156226,0.0004205139,0.0002174383],"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":[0.0001687111,0.00009385031,0.003882022,0.0002807502,0.0001884407,0.0004554562,0.0004994545,0.3379769,0.01208989,0.5400361,0.004686526,0.09964196],"study_design_scores_gemma":[0.00001832981,0.0000884641,0.0006405105,0.00003196474,0.00002234648,0.0001619197,0.00003855434,0.412,0.001652586,0.5828871,0.002439046,0.00001909184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06018839,0.0007452032,0.9289852,0.002336804,0.000118291,0.00005723747,0.0001189079,0.0006195404,0.006830401],"genre_scores_gemma":[0.8363662,0.001599084,0.1524578,0.001609655,0.0004480852,0.0003059866,0.0004359456,0.0005336402,0.006243553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003081242,"threshold_uncertainty_score":0.01629537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03042273223014454,"score_gpt":0.2379050445550649,"score_spread":0.2074823123249203,"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."}}