{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001448145,0.0005406486,0.00040514,0.001145707,0.0009062768,0.00273231,0.0007284283,0.00102852,0.004144866],"category_scores_gemma":[0.002936688,0.0003515423,0.001316706,0.0005843031,0.004654317,0.005091657,0.001474481,0.001900213,0.0006887137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001074589,"about_ca_system_score_gemma":0.000701971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009431402,"about_ca_topic_score_gemma":0.0006083887,"domain_scores_codex":[0.9992427,0.0003240826,0.00005231501,0.0001248747,0.0001891098,0.00006695909],"domain_scores_gemma":[0.9989491,0.0004951081,0.000118667,0.0001826057,0.000179045,0.00007552582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001261273,0.000007535694,0.00008110301,0.00001829312,0.000003790646,0.00005878414,0.0001556236,0.003716461,0.0007583508,0.9916767,0.0003508303,0.003159917],"study_design_scores_gemma":[0.000004014863,0.000009815478,0.00003560548,0.00000967292,0.000001961421,0.00003864599,0.00003369037,0.01965907,0.0002906801,0.9778244,0.002086173,0.000006250818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03936396,0.0009947299,0.9294835,0.002497055,0.0003111552,0.0000346744,0.0001889993,0.0002012659,0.02692461],"genre_scores_gemma":[0.757824,0.001445399,0.2254576,0.0008783537,0.0007029929,0.0001548775,0.0002735008,0.0002195565,0.01304372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004144866,"threshold_uncertainty_score":0.01386601,"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."}}