{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002298455,0.001015534,0.001450666,0.001003419,0.001278141,0.0007529391,0.00364749,0.0006868722,0.0001480274],"category_scores_gemma":[0.0004031958,0.001099325,0.0006306007,0.00242457,0.0004035712,0.001161925,0.005292187,0.002020524,0.0002147857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003597456,"about_ca_system_score_gemma":0.0003925306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001620891,"about_ca_topic_score_gemma":0.00004675563,"domain_scores_codex":[0.9929973,0.001510581,0.001061157,0.002687635,0.0003691003,0.001374211],"domain_scores_gemma":[0.9950143,0.000286179,0.001306194,0.001854809,0.000935779,0.0006027133],"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":[0.0006023418,0.0001268129,0.002964553,0.0003252105,0.0003258005,0.0001230245,0.009424975,0.970917,0.0008331348,0.004778035,0.0001827956,0.009396303],"study_design_scores_gemma":[0.002002327,0.000354635,0.0002505841,0.002405811,0.0002189806,0.00001436298,0.0004363035,0.9839311,0.0009285422,0.0003735691,0.007846357,0.001237377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4726858,0.0004042421,0.523342,0.0002564047,0.00131406,0.0005050792,0.000001161231,0.0002743149,0.001216891],"genre_scores_gemma":[0.9895288,0.0005798972,0.004360103,0.0002866663,0.0009160893,0.000002796875,0.000008906577,0.00008845393,0.004228286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5189819,"threshold_uncertainty_score":0.9991457,"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."}}