Independent scholarship · Open accessThe monthly digest

Editorially reviewed

Differential Topology of Parametrized Neural Networks

Differential-topological conditions for smooth parametrized networks. Affine readouts control first jets of immersed features. Circle and torus examples exhibit decision-boundary monodromy and a stabilizer obstruction. The paper proves sharp uniform reconstruction bounds for spheres.

Anonymous← All research

Scope

The paper applies the relative mapping objects, transversality results, and derived intersection models of Differential Topology in Higher Categories to smooth parametrized neural networks. It also builds on Representation Theory of Parametrized Neural Models on Spaces.

Readouts and decision boundaries

An affine readout of an immersed smooth feature map is submersive on first jets. Free final biases give generic transverse classification boundaries even when the feature map is not immersive. A quadratic circle classifier gives an explicit fold discriminant. A different exact circle network has regular signed boundary points with cyclic monodromy in the parameters. Its persistence over the parameter circle retains transport data that its individual fiber barcodes forget.

Symmetry and reconstruction

At a fixed parameter, its stabilizer representation can rule out surjectivity of the normal derivative. A reflected torus with two sign outputs exhibits a derived obstruction line, even though a transforming bias makes the total zero equation regular. Smooth exact ambient reconstruction through a fixed Euclidean encoder is possible precisely when the encoder embeds the compact data manifold. For the unit sphere and continuous ambient decoders with latent width at most the sphere dimension, the optimal uniform error is one.

Evidence and authorship

The manuscript gives proofs and explicit worked models. It is submitted under an anonymous byline and was prepared with AI assistance in drafting, typesetting, and checking. The attached LaTeX file contains the entire manuscript and is designated for text indexing upon publication.

Reproducibility artifacts

differential-topology-of-parametrized-neural-networks.pdf · 433,535 bytes · Download
SHA-256 e9a734cb600d03edaed3fb4a41ad2140235b813e2f034ea2cd9201ad2d8983b9

differential-topology-of-parametrized-neural-networks.tex · 46,186 bytes · Read in browser · Download
Text indexing selected · View indexed source
SHA-256 8ac764137618f880261edd34deb5ba273f7258c13df12980eb400385eb5ab93f

Discussion

Open a careful, constructive conversation about this note.

Comments appear after editorial approval.