{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001332544,0.0004139773,0.0007850285,0.0003591327,0.0002086584,0.0007003333,0.001736687,0.0002913259,0.00004146376],"category_scores_gemma":[0.0002049917,0.0003344428,0.0002267077,0.0003953787,0.00002763881,0.0003478482,0.003381942,0.001199106,0.00007645568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007051498,"about_ca_system_score_gemma":0.0001518784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001128053,"about_ca_topic_score_gemma":0.0000111021,"domain_scores_codex":[0.9969558,0.0004070324,0.0006930754,0.0009101761,0.0004787457,0.0005552145],"domain_scores_gemma":[0.9980569,0.0001350046,0.0004225934,0.001013372,0.000227613,0.0001444672],"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":[0.00004298531,0.00002700509,0.0005994276,0.0002633341,0.00007643476,0.000004070817,0.006429023,0.9450399,0.001322918,0.001368599,0.0007618556,0.04406448],"study_design_scores_gemma":[0.0005814729,0.00006616888,0.00007141883,0.0010289,0.00001820449,0.000005399861,0.00007743859,0.9814641,0.001576053,0.00007319,0.01454814,0.0004895279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0947766,0.001383664,0.8946565,0.001754392,0.001527661,0.0005477438,3.096319e-7,0.0005925375,0.004760557],"genre_scores_gemma":[0.933028,0.00007943613,0.06142482,0.0006473094,0.0004283267,0.00003620853,0.000007242024,0.00004601593,0.00430262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8382514,"threshold_uncertainty_score":0.9999108,"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."}}