Category Theory in Machine Learning
arXiv:2106.07032
Abstract
Over the past two decades machine learning has permeated almost every realm of technology. At the same time, many researchers have begun using category theory as a unifying language, facilitating communication between different scientific disciplines. It is therefore unsurprising that there is a burgeoning interest in applying category theory to machine learning. We aim to document the motivations, goals and common themes across these applications. We touch on gradient-based learning, probability, and equivariant learning.
References in corpus (12)
- Language Models are Few-Shot Learners
- Gauge Equivariant Convolutional Networks and the Icosahedral CNN
- Persistent Clustering and a Theorem of J. Kleinberg
- Reverse Derivative Ascent: A Categorical Approach to Learning Boolean Circuits
- Bayesian Updates Compose Optically
- Lenses and Learners
- Consistency constraints for overlapping data clustering
- Poly: An abundant categorical setting for mode-dependent dynamics
- Compositional Deep Learning
- On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps
- Differentiable Causal Computations via Delayed Trace
- Characterizing the invariances of learning algorithms using category theory