{"id":"W2945839892","doi":"10.48550/arxiv.1905.10901","title":"Seeing Convolution Through the Eyes of Finite Transformation Semigroup Theory: An Abstract Algebraic Interpretation of Convolutional Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convolutional neural network; Semigroup; Computer science; Convolution (computer science); Interpretation (philosophy); Transformation (genetics); Theoretical computer science; Artificial intelligence; Algebra over a field; Mathematics; Artificial neural network; Algorithm; Discrete mathematics; Pure 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":[0.001591452,0.0002844124,0.0004251078,0.000120501,0.0001720172,0.00007405325,0.001026777,0.0002612789,0.0003796486],"category_scores_gemma":[0.0001493491,0.0002495994,0.0001716579,0.0002669975,0.0006007365,0.0009604274,0.0002943779,0.0004399537,0.00002289124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001110402,"about_ca_system_score_gemma":0.000125946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004493641,"about_ca_topic_score_gemma":0.00003676771,"domain_scores_codex":[0.9976358,0.0007094623,0.0005495631,0.0005954229,0.000210382,0.0002993728],"domain_scores_gemma":[0.9973471,0.0005974532,0.001090735,0.0006553158,0.0002583244,0.00005103604],"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":[0.0002592112,0.00004376309,0.0009597861,0.0001975097,0.00002012064,0.000001905903,0.001889992,0.9332259,0.0136634,0.04963704,0.000007239925,0.00009409834],"study_design_scores_gemma":[0.0003030838,0.0001049527,0.006130388,0.0001902412,0.00009197139,0.000002756192,0.0005389539,0.9733295,0.002725967,0.01633014,0.00001070101,0.0002413885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6112336,0.00005387136,0.3871131,0.00002389614,0.0007147733,0.0003155596,0.00005881661,0.00005212844,0.0004342126],"genre_scores_gemma":[0.999306,0.00004103492,0.0003194334,0.00004791225,0.00006851787,0.000001865507,0.0001271095,0.00001877409,0.00006940348],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3880723,"threshold_uncertainty_score":0.9999956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0347903735301581,"score_gpt":0.2116611838993739,"score_spread":0.1768708103692158,"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."}}