{"id":"W2947024452","doi":"10.48550/arxiv.1906.00443","title":"Dimensionality compression and expansion in Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Curse of dimensionality; Artificial neural network; Computer science; Artificial intelligence; Generalization; Manifold (fluid mechanics); Nonlinear dimensionality reduction; Regularization (linguistics); Dimensionality reduction; Stochastic gradient descent; Deep learning; Gradient descent; Noise (video); Pattern recognition (psychology); Machine learning; Mathematics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002656377,0.0002988256,0.0003883285,0.000150321,0.000120024,0.0001108476,0.0007675691,0.0002787841,0.00001501648],"category_scores_gemma":[0.00001958947,0.0003034643,0.0001121355,0.0003168554,0.00008775498,0.0004232501,0.002733229,0.0005743105,0.000008468917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008601727,"about_ca_system_score_gemma":0.00004051433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002209412,"about_ca_topic_score_gemma":0.00007967856,"domain_scores_codex":[0.9979047,0.000362778,0.0002062143,0.001111224,0.00008339868,0.0003316806],"domain_scores_gemma":[0.9985696,0.0001895158,0.0001780875,0.0008461676,0.0000855196,0.0001311249],"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":[0.00002805745,0.00004492998,0.006542058,0.00001896354,0.00001522175,0.00008591888,0.00007537114,0.9874665,0.00004382409,0.002727915,0.00007874486,0.002872555],"study_design_scores_gemma":[0.0004046585,0.00002733264,0.01443882,0.00008356207,0.00001628991,0.000002228162,0.000021689,0.9809147,0.00003726676,0.003688852,0.00004678546,0.0003178613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.240753,0.0002989755,0.7576331,0.00008933458,0.00071147,0.0002397359,0.000002084832,0.00005569686,0.0002165829],"genre_scores_gemma":[0.9977729,0.0002014513,0.001640252,0.0001522606,0.00007744384,6.517334e-7,0.00001261701,0.0000119344,0.0001304765],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7570199,"threshold_uncertainty_score":0.9999418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04547687358783814,"score_gpt":0.1824946952936411,"score_spread":0.1370178217058029,"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."}}