Independent scholarship · Open accessThe monthly digest

Editorially reviewed

Algebraic and Differential Topology in Machine Learning and AI: Obstructions, Invariants, and Counts

Classical topology as constraints on neural networks that hold for every choice of weights. Obstructions: bottlenecks, rotation codes, frames on meshes, pieces, depth and width. Invariants: Hodge diffusion, coefficients, Rips complexes, persistence. Counts: junctions of decision regions, fixed points of attractors, degree, zeros of odd networks. Two-column paper, 9 pp., 9 figures, 25 checks.

Anonymous← All research

Algebraic and Differential Topology in Machine Learning and AI: Obstructions, Invariants, and Counts

A neural network is a continuous map, usually piecewise linear, and the classical theorems of algebraic and differential topology say what continuous maps can and cannot do. This paper collects their consequences for learning systems under three headings and pairs each qualitative statement with a computed one. It is the companion of the volume Algebraic and Differential Topology in Higher Categories, a treatment of two monographs of L. S. Pontryagin, and it uses that volume's first part (homology, Sperner's lemma, the Lefschetz number) and its rotation groups.

Format. Two-column paper, 9 pages, 14 numbered statements with status tags (classical, literature, reformulation, observation), 9 figures, a summary table, 30 references, and a companion script with 25 computational checks.

The organizing idea

Topological statements about networks hold for every choice of weights, because they are statements about functors. An obstruction is a diagram that a functor forbids, an invariant is the functor's value, and a count is that value when it is an integer which the geometry must realize as a number of points. The simplest obstruction is the one behind Brouwer's theorem. A retraction $r$ of the ball onto its boundary would make the top row compose to the identity, and homology would then factor the identity of $\mathbb Z$ through zero:

$$\begin{CD} S^{n-1} @>>> D^n @>{r}>> S^{n-1} \\ @V{H_{n-1}}VV @V{H_{n-1}}VV @VV{H_{n-1}}V \\ \mathbb Z @>>> 0 @>>> \mathbb Z \end{CD}$$

The other obstructions in the paper have the same shape, with the fundamental group, the degree or the Euler characteristic in place of $H_{n-1}$.

Results: qualitative statement, then its quantitative form

TopicQualitativeQuantitative (recomputed by the script)
Bottleneckno continuous injective code of $S^n$ in $\mathbb R^n$ (Borsuk-Ulam)worst-case reconstruction error at least $1$ for every encoder and decoder, attained by projection; collisions located for $200$ and $40$ random encoders
Rotationsno continuous quaternion or Euler-angle target on a non-contractible loop, since $\pi_1(\mathrm{SO}(3))=\mathbb Z/2$; a six-dimensional code is continuousalong a full turn in $2000$ steps: jumps $2.0000$ and $3.1416$ against steps of $0.004$; Gram-Schmidt decoder with Lipschitz constant at most $1.40$
Meshesno global frame field unless $\chi=0$; among spheres only for $n=1,3,7$index sums $2,2,0,1,0$ on five triangulated surfaces; the quaternion frame on $S^3$ orthonormal to $10^{-15}$
Piecesa closed curve of $N$ linear pieces winds fewer than $N/2$ times$z\mapsto z^3$ sampled at $5,7,12$ points winds $-2,3,3$ times
Depthcomposition multiplies degreedepth $L$ gives degree $2^L$ with $4\cdot2^L$ pieces for $L\le6$; one hidden layer needs more than $2^L-2$ units
Widthwith an injective activation, $n$ units per layer cannot enclose a bounded region; $n+1$ rectifier units can$30$ networks of depth four: both regions connected and unbounded; a three-unit island with value $1$ inside and at most $-2.46$ outside
Hodge diffusionconverges to real homology, and is blind to torsionkernels equal to Betti numbers on six complexes; gap $1.5858$, $99$ layers for $10^{-11}$; projective plane and disc agree over $\mathbb R$ and differ over $\mathbb F_2$
Rips complexesspheres of higher dimension at large scales are artefacts of the constructionFor twelve equally spaced points, $S^1$ occurs at scales one through three sample spacings, a wedge of three $S^2$ at four, and $S^5$ at five.
Persistencediagrams are stable; the number of their points is notbottleneck distance at most the perturbation in $60$ trials, with equality attained; the number of points changed in $35$
Decision regionssmall regions of the $n$-cube meet $n+1$ at a time (Lebesgue)$13$ to $18$ triple points for prototype classifiers of the square; $143$ to $174$ quadruple points in the cube
Sperner walka fixed point is found by following a path$13, 25, 50, 97$ steps on grids of side $16, 32, 64, 128$
Attractorsfixed points have total index $1-d$ on a circle, $0$ on a torus, $2$ on a sphere$5,7,6,9,8$ fixed points with index sums $3,1,0,-1,-2$ for $d=-2,0,1,2,3$; four zeros on a torus
Normalized outputsthe degree changes only when the output passes through zerodegree $1\to0$ at bias $1.2930$, where the smallest output norm is $10^{-4}$
Odd networksAn odd network $\mathbb R^{n+1}\to\mathbb R^n$ has a zero on every origin-centred sphere. If all zeros of a smooth scalar output on a circle are simple, their number is $2$ modulo $4$.A sign scan found $2$ crossings in $193$ of $200$ networks and $6$ in the other $7$. A bias of $10$ makes the last network's output positive.

Reading the table

What is and is not claimed

No new theorem. The theorems are classical, and several of the applications are in the literature cited (the rotation codes, gauge-equivariant convolution, Hodge Laplacians, the Vietoris-Rips complexes of the circle, stability of persistence, narrow networks). The statements tagged observation or reformulation are elementary and may be in the literature in other words: the constant in the bottleneck bound, the piece count for winding, the depth statement for degree, and the remark on coefficients.

Limits. The data are idealized as exactly a sphere, a rotation group or a circle. The models are small and exact, with complexes of at most a few hundred simplices, and no trained network was examined. The narrow-network theorem is proved for activations that are homeomorphisms of the line; for the rectifier only a weaker cited statement survives. The complexity statement about Sperner walks is for fixed-point problems given by circuits. The second monograph of the source, on framed manifolds and the first stable stems, has no application here beyond the rotation groups, and none was forced.

Files

Status and authorship

Contribution. A synthesis: classical topology applied to network architectures, with each qualitative statement paired with a computed one and every number reproducible.

Limitations. As above. In addition, the references were assembled from memory except for three whose details were checked online on 19 November 2026 (Zhou et al. on rotation representations, Adamaszek and Adams on the Vietoris-Rips complexes of the circle, and the 2024 position paper on topological deep learning), and nothing has been independently refereed. The script's checks are instances, not proofs. Corrections are welcome.

AI assistance. The text was drafted and typeset with a large language model (Anthropic's Claude) under the direction of the submitting author, who is responsible for it. Generative AI assisted with drafting, literature recall, mathematical consistency checks, computation, figures and typesetting.

Reproducibility artifacts

algebraic-and-differential-topology-in-machine-learning-and-ai.pdf · 275,654 bytes · Download
SHA-256 eddaf72f80f2297f53cd66331c1a85d26085b54df42c289dfb18c3999a1f82b8

algebraic-and-differential-topology-in-machine-learning-and-ai.tex · 123,764 bytes · Read in browser · Download
Text indexing selected · View indexed source
SHA-256 29b3cf5d7b1fbd398b4564ec81082c50ec81c37ed9e5cdbf95cd8d2cb1c50a1e

verify-topology-learning.py · 57,869 bytes · Download
Text indexing selected · View indexed source
SHA-256 38418e8cf834c1fe19c0e7c8f14ff79be49761f874b6998bac644d8186efade1

Discussion

Open a careful, constructive conversation about this note.

Comments appear after editorial approval.