activity
20152022
most citedBialgebraic Semantics for Logic Programming

32 citations · 60 across the 4 of their papers we have counts for

collaborators

14 papers

cs.LG2022

Categories of Differentiable Polynomial Circuits for Machine Learning

Paul Wilson, Fabio Zanasi

Reverse derivative categories (RDCs) have recently been shown to be a suitable semantic framework for studying machine learning algorithms. Whereas emphasis has been put on trainin…

cs.PL20217 cited

Functorial String Diagrams for Reverse-Mode Automatic Differentiation

Mario Alvarez-Picallo, Dan R. Ghica, David Sprunger +1

We enhance the calculus of string diagrams for monoidal categories with hierarchical features in order to capture closed monoidal (and cartesian closed) structure. Using this new s…

cs.LG2021

Categorical Foundations of Gradient-Based Learning

G. S. H. Cruttwell, Bruno Gavranović, Neil Ghani +2

We propose a categorical semantics of gradient-based machine learning algorithms in terms of lenses, parametrised maps, and reverse derivative categories. This foundation provides…

cs.LO202116 cited

Reverse Derivative Ascent: A Categorical Approach to Learning Boolean Circuits

Paul Wilson, Fabio Zanasi

We introduce Reverse Derivative Ascent: a categorical analogue of gradient based methods for machine learning. Our algorithm is defined at the level of so-called reverse differenti…

cs.FL2020

A String Diagrammatic Axiomatisation of Finite-State Automata

Robin Piedeleu, Fabio Zanasi

We develop a fully diagrammatic approach to the theory of finite-state automata, based on reinterpreting their usual state-transition graphical representation as a two-dimensional…

cs.LO2020

Contextual Equivalence for Signal Flow Graphs

Filippo Bonchi, Robin Piedeleu, Pawel Sobocinski +1

We extend the signal flow calculus---a compositional account of the classical signal flow graph model of computation---to encompass affine behaviour, and furnish it with a novel op…