English
Related papers

Related papers: Lenses and Learners

200 papers

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Martina G. Vilas , Timothy Schaumlöffel , Gemma Roig

Lenses are an important tool in applied category theory. While individual lenses have been widely used in applications, many of the mathematical properties of the corresponding categories of lenses have remained unknown. In this paper, we…

Category Theory · Mathematics 2022-11-04 Emma Chollet , Bryce Clarke , Michael Johnson , Maurine Songa , Vincent Wang , Gioele Zardini

We introduce the normal produoidal category of monoidal contexts over an arbitrary monoidal category. In the same sense that a monoidal morphism represents a process, a monoidal context represents an incomplete process: a piece of a…

Logic in Computer Science · Computer Science 2023-01-30 Matt Earnshaw , James Hefford , Mario Román

In some bicategories, the 1-cells are `morphisms' between the 0-cells, such as functors between categories, but in others they are `objects' over the 0-cells, such as bimodules, spans, distributors, or parametrized spectra. Many…

Category Theory · Mathematics 2010-03-15 Michael A. Shulman

Optics are bidirectional data accessors that capture data transformation patterns such as accessing subfields or iterating over containers. Profunctor optics are a particular choice of representation supporting modularity, meaning that we…

Programming Languages · Computer Science 2024-08-07 Bryce Clarke , Derek Elkins , Jeremy Gibbons , Fosco Loregian , Bartosz Milewski , Emily Pillmore , Mario Román

A type theory is presented that combines (intuitionistic) linear types with type dependency, thus properly generalising both intuitionistic dependent type theory and full linear logic. A syntax and complete categorical semantics are…

Logic in Computer Science · Computer Science 2026-05-07 Matthijs Vákár

In this paper, we study the machine learning elements which we are interested in together as a machine learning system, consisting of a collection of machine learning elements and a collection of relations between the elements. The…

Machine Learning · Computer Science 2025-02-05 Xiuzhan Guo

We propose a categorical semantics for machine learning algorithms in terms of lenses, parametric maps, and reverse derivative categories. This foundation provides a powerful explanatory and unifying framework: it encompasses a variety of…

Machine Learning · Computer Science 2024-04-02 Geoffrey S. H. Cruttwell , Bruno Gavranovic , Neil Ghani , Paul Wilson , Fabio Zanasi

The category $\mathbf{Rel}$ is the category of sets (objects) and relations (morphisms). Equipped with the direct product of sets, $\mathbf{Rel}$ is a monoidal category. Moreover, $\mathbf{Rel}$ is a locally posetal 2-category, since every…

Rings and Algebras · Mathematics 2017-11-27 Anna Jenčová , Gejza Jenča

Incorporating geometric transformations that reflect the relative position changes between an observer and an object into computer vision and deep learning models has attracted much attention in recent years. However, the existing proposals…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Nishan Khatri , Agnibh Dasgupta , Yucong Shen , Xin Zhong , Frank Y. Shih

We introduce a notion of parity for formal morphisms between invertible objects and use it to prove a corresponding coherence theorem. Parity is conceptually similar to the sign of underlying permutations, but not defined as such. To give…

Category Theory · Mathematics 2026-04-17 Nick Gurski , Niles Johnson

Bidirectional transformations (bx) have primarily been modeled as pure functions, and do not account for the possibility of the side-effects that are available in most programming languages. Recently several formulations of bx that use…

Programming Languages · Computer Science 2017-09-12 Faris Abou-Saleh , James Cheney , Jeremy Gibbons , James McKinna , Perdita Stevens

We establish a correspondence between modules and spans of algebras within a general monoidal 2-category $\mathfrak{C}$. Specifically, for an algebra $A$ in $\mathfrak{C}$, we construct a normalized lax 3-functor from the 2-category of…

Category Theory · Mathematics 2025-12-03 Hao Xu

The goal of this paper is to prove coherence results with respect to relational graphs for monoidal monads and comonads, i.e. monads and comonads in a monoidal category such that the endofunctor of the monad or comonad is a monoidal functor…

Category Theory · Mathematics 2010-01-08 K. Dosen , Z. Petric

Networks can be combined in various ways, such as overlaying one on top of another or setting two side by side. We introduce "network models" to encode these ways of combining networks. Different network models describe different kinds of…

Category Theory · Mathematics 2020-07-22 John C. Baez , John Foley , Joe Moeller , Blake S. Pollard

We use machine learning to classify examples of braids (or flat braids) as trivial or non-trivial. Our ML takes form of supervised learning using neural networks (multilayer perceptrons). When they achieve good results in classification, we…

Geometric Topology · Mathematics 2023-07-25 Alexei Lisitsa , Mateo Salles , Alexei Vernitski

Layered monoidal theories provide a categorical framework for studying scientific theories at different levels of abstraction, via string diagrammatic algebra. We introduce models for three closely related classes of layered monoidal…

Category Theory · Mathematics 2026-02-27 Leo Lobski , Fabio Zanasi

We universally characterize the produoidal category of monoidal lenses over a monoidal category. In the same way that each category induces a cofree promonoidal category of spliced arrows, each monoidal category induces a cofree produoidal…

Category Theory · Mathematics 2024-04-10 Mario Román

Linguistic similarity is multi-faceted. For instance, two words may be similar with respect to semantics, syntax, or morphology inter alia. Continuous word-embeddings have been shown to capture most of these shades of similarity to some…

Computation and Language · Computer Science 2019-07-05 Ryan Cotterell , Hinrich Schütze

Incorporating symmetries can lead to highly data-efficient and generalizable models by defining equivalence classes of data samples related by transformations. However, characterizing how transformations act on input data is often…

Machine Learning · Computer Science 2022-07-04 Jung Yeon Park , Ondrej Biza , Linfeng Zhao , Jan Willem van de Meent , Robin Walters