Independent scholarship · Open accessThe monthly digest

Indexed text attachment

topos-actions-in-machine-learning-and-ai.tex

Source for Topos Actions in Machine Learning and Artificial Intelligence

View paper · Download original file

Lines 981–1080 of 1207. Source text is displayed literally.

981these linear filters with such activations to obtain a982global nonlinear layer. A sum of the three output983coordinates then gives a scalar readout, invariant under984both the local group and the frame transition.985 986A simple regression calculation gives a training987interpretation with a specified observation law.988In a local frame draw $x=e_j$ uniformly over $j$,989draw a hidden sign $\varepsilon\in\{\pm1\}$ fairly990and independently, and observe the target991$y=R^\varepsilon x$. Inverting the frame sends992$(x,y,\varepsilon)$ to $(Sx,Sy,-\varepsilon)$, so993the law descends even though a deterministic forward994shift $R$ does not define a flat global filter.995The least-squares estimator conditional on $x$ is996$(R+R^2)x/2$, an admissible flat filter.997The two conditional target vectors are distinct basis998vectors, so each lies squared distance $1/2$ from999their mean. The best expected squared error using1000only $x$ is therefore $1/2$. The rule $(x,\varepsilon)\mapsto R^\varepsilon x$ has zero error1001if the sign is supplied with its frame transition. The ambiguity here1002is a stated property of the observation law.1003Monodromy supplies the transformation of the hidden1004sign and the constraint on flat filters.1005\par1006\section{Conclusion}1007 1008The literature provides several operational cases of learning1009with symmetry-sensitive structure. Nominal automata support1010active queries over infinitely many names with finitely1011described orbits. Sheaf neural networks use local incidence1012geometry, and groupoid-equivariant networks use transformations1013that are defined only on parts of the input space. Topos and1014stack semantics also supply formal descriptions of network1015behavior and symbolic reasoning. The type of action differs1016across these examples.1017 1018The two models in Section~\ref{sec:applications} give concrete1019consequences of following the type of action through to the1020parameters and observations. A central quotient identifies1021the input orbit as the information available to every1022nuisance-invariant predictor. The circle group sheaf imposes1023a transition law on one learnable coefficient, even though1024its global group of sections is trivial. An equivariant1025optimizer requires compatible metric, loss, and data transport1026in addition to compatible layers. The topological statements1027describe admissible realizations. Prediction error and1028optimization depend on the observation law and update rule1029specified for the model.1030\par1031\begin{thebibliography}{99}1032\small\raggedright1033 1034\bibitem{abramsky-contextuality}1035S. Abramsky and A. Brandenburger. The sheaf-theoretic structure1036of non-locality and contextuality.1037\emph{New J. Phys.} 13 (2011), 113036.1038\href{https://doi.org/10.1088/1367-2630/13/11/113036}{DOI}.1039 1040\bibitem{amari-natural}1041S.-i. Amari. Natural gradient works efficiently in learning.1042\emph{Neural Computation} 10(2) (1998), 251--276.1043\href{https://doi.org/10.1162/089976698300017746}{DOI}.1044 1045\bibitem{topos-actions}1046Anonymous. \emph{Actions of Toposes on Toposes:1047Geometric Actions, Internal Symmetry, and Quotient Constructions}.1048Companion manuscript, submitted to Higher Categorical Semantics, 2026.1049 1050\bibitem{barbe-topos-automata}1051K. Barb\'e. \emph{Learning Functorial Automata in Topoi}.1052Research internship report, IRIF, 2024.1053\href{https://www.irif.fr/~kbarbe/files/msc.pdf}{Report}.1054 1055\bibitem{belfiore-bennequin}1056J.-C. Belfiore and D. Bennequin.1057Topos and stacks of deep neural networks. Preprint, version 3, 2022.1058\href{https://arxiv.org/abs/2106.14587}{arXiv:2106.14587}.1059 1060\bibitem{bodnar-nsd}1061C. Bodnar, F. Di Giovanni, B. P. Chamberlain, P. Li\`o, and M. M. Bronstein.1062Neural sheaf diffusion: A topological perspective on heterophily1063and oversmoothing in GNNs.1064In \emph{Advances in Neural Information Processing Systems} 35, 2022.1065\href{https://papers.neurips.cc/paper_files/paper/2022/hash/75c45fca2aa416ada062b26cc4fb7641-Abstract-Conference.html}{Proceedings}.1066 1067\bibitem{caramello-raven}1068O. Caramello. \emph{Relative Toposes for Artificial General1069Intelligence}, part 2. CentraleSup\'elec, July 2025.1070\href{https://www.oliviacaramello.com/Talks/RelativeToposesAGI_part2.pdf}{Course slides}.1071 1072\bibitem{chen-augmentation}1073S. Chen, E. Dobriban, and J. H. Lee.1074A group-theoretic framework for data augmentation.1075\emph{J. Mach. Learn. Res.} 21(245) (2020), 1--71.1076\href{https://jmlr.org/papers/v21/20-163.html}{Journal article}.1077 1078\bibitem{cohen-geiger-weiler}1079T. S. Cohen, M. Geiger, and M. Weiler.1080A general theory of equivariant CNNs on homogeneous spaces.