2 citations · 2 across the 6 of their papers we have counts for
6 papers
Weaves, Wires, and Morphisms: Formalizing and Implementing the Algebra of Deep Learning
Vincent Abbott, Gioele Zardini
Despite deep learning models running well-defined mathematical functions, we lack a formal mathematical framework for describing model architectures. Ad-hoc notation, diagrams, and…
Accelerating Machine Learning Systems via Category Theory: Applications to Spherical Attention for Gene Regulatory Networks
Vincent Abbott, Kotaro Kamiya, Gerard Glowacki +3
How do we enable artificial intelligence models to improve themselves? This is central to exponentially improving generalized artificial intelligence models, which can improve thei…
FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness
Vincent Abbott, Gioele Zardini
Optimizing deep learning algorithms currently requires slow, manual derivation, potentially leaving much performance untapped. Methods like FlashAttention have achieved a x6 perfor…
Diagrammatic Negative Information
Vincent Abbott, Gioele Zardini
The flow of information through a complex system can be readily understood with category theory. However, negative information (e.g., what is not possible) does not have an immedia…
Functor String Diagrams: A Novel Approach to Flexible Diagrams for Applied Category Theory
Vincent Abbott, Gioele Zardini
The study of abstraction and composition - the focus of category theory - naturally leads to sophisticated diagrams which can encode complex algebraic semantics. Consequently, thes…
Neural Circuit Diagrams: Robust Diagrams for the Communication, Implementation, and Analysis of Deep Learning Architectures
Vincent Abbott
Diagrams matter. Unfortunately, the deep learning community has no standard method for diagramming architectures. The current combination of linear algebra notation and ad-hoc diag…