Indexed text attachment
parametrized-neural-networks-and-their-representations-in-differential-topology.tex
Source for Parametrized Neural Networks and Their Representations in Differential Topology
View paper · Download original file
Lines 181–280 of 2141. Source text is displayed literally.
181\newcommand{\loss}{\mathcal{L}}182 183% ---------- tikz styles ----------184\tikzset{185 ogbox/.style={draw, thick, rounded corners=2pt, minimum width=1.25cm, minimum height=1.05cm, fill=black!4},186 fw/.style={-{Stealth[length=5pt]}, thick, fwd},187 bw/.style={-{Stealth[length=5pt]}, thick, bwd, densely dashed},188 dec/.style={circle, fill, inner sep=1.7pt},189 nat/.style={circle, draw, thick, fill=white, inner sep=1.7pt},190 leaf/.style={inner sep=2pt, font=\small},191 lab/.style={font=\small, inner sep=1.5pt},192 infoset/.style={densely dashed, thick, accent},193 st/.style={circle, draw, thick, fill=white, inner sep=1.6pt},194 ty/.style={rectangle, draw, thick, fill=black!8, inner sep=2.6pt},195}196\newcommand{\sol}[1]{\par\medskip\noindent\textbf{#1.}\enspace\ignorespaces}197\newcommand{\bookauthor}{Anonymous}198\newcommand{\DT}[1]{\cite[#1]{DTHC}}199\newcommand{\ev}{\mathrm{ev}}200%% ---- end preamble.tex ----201\begin{document}202\frontmatter203%% ---- begin front.tex ----204\begin{titlepage}205\thispagestyle{empty}206\vspace*{1.1in}207\noindent{\Large\scshape\color{accent} Higher Categorical Semantics}\par208\vspace{0.9in}209\noindent{\fontsize{28}{36}\selectfont\bfseries\raggedright Parametrized Neural\\ Networks and Their\\ Representations in\\ Differential Topology\par}210\vspace{0.35in}211\noindent{\Large\itshape Families of maps, transversality,\\[2pt] surgery along training, and isotopy}\par212\vfill213\noindent\begin{tikzpicture}[x=1cm,y=1cm]214 \node[ogbox] (th) at (0,0.7) {$\Theta$};215 \node[ogbox] (x) at (0,-0.7) {$X$};216 \node[ogbox,minimum width=1.6cm] (F) at (2.6,0) {$F$};217 \node[lab] (y) at (5.0,0) {$Y$};218 \draw[fw] (th) -- (F);219 \draw[fw] (x) -- (F);220 \draw[fw] (F) -- (y);221 \node[lab] at (6.1,0) {$=$};222 \node[lab] (t2) at (7.2,0) {$\Theta$};223 \node[lab] (m) at (9.6,0) {$[X,Y]$};224 \draw[fw,black] (t2) -- (m);225\end{tikzpicture}\par226\vspace{0.5in}227\noindent{\large \bookauthor}\par228\vspace{4pt}229\noindent{\small 2026}230\end{titlepage}231 232\thispagestyle{empty}233\vspace*{\fill}234{\small235\noindent\textbf{About this text.}236This monograph applies the results of \emph{Differential Topology in Higher Categories} \cite{DTHC}, the237higher-categorical treatment of M.~W.~Hirsch's \emph{Differential Topology} \cite{Hir76} in the same series, to smooth238families of maps defined by neural network architectures. It is written to be read after that volume and239cites it by theorem number, in the form \DT{4.5}. It is an independent work and is not affiliated with or240endorsed by the publisher of Hirsch's book.241 242\medskip243\noindent\textbf{Status of results.}244Every numbered statement carries a tag: \textsf{classical} (standard mathematics, attributed),245\textsf{literature} (established in the machine learning or mathematical literature, attributed),246\textsf{reformulation} (a known result restated or specialized, with the derivation given here),247\textsf{observation} (an elementary consequence we have not found stated in this form), or248\textsf{programme} (a direction, not a result). The statements tagged \textsf{reformulation} and249\textsf{observation} are corollaries of classical differential topology applied to parametrized families;250none is claimed as a new theorem of differential topology, and none says anything quantitative about251training or generalization.252 253\medskip254\noindent\textbf{Authorship and assistance.}255The text was drafted and typeset with a large language model (Anthropic's Claude) under the direction of256the submitting author, who is responsible for it. Generative AI assisted with drafting, literature recall,257mathematical consistency checks, computation, and typesetting. The numerical examples and finite instances258of the structural claims are recomputed by the accompanying script \texttt{verify-parametrized-networks.py}259(\cref{app:computations}), which uses small networks implemented in pure Python. Proofs and bibliographic260details have not been independently refereed; corrections are welcome.261 262\medskip263\noindent Open access. Rights remain with the author.264}265\clearpage266 267\tableofcontents268 269\chapter{Preface}270 271A neural network architecture is a smooth map $F\colon\Theta\times X\to Y$: a family of maps from inputs to272outputs, parametrized by weights. Differential topology, in the form Hirsch gave it, is the study of what is273true of a generic member of a family of maps and of what happens along a generic path in one. The fit is274close enough that most of the qualitative questions asked about networks have answers that are corollaries275of theorems proved before 1976, once the questions are phrased as questions about families.276 277Is the decision boundary of a classifier a manifold? For almost every value of the parameters, yes, by the278parametric transversality theorem, provided the last layer has a bias. How does the boundary change during279training? By ambient isotopy, except at isolated times, at each of which it undergoes one surgery whose type280is the index of a critical point; this is Morse theory on the trace of the boundary. What is the set of