bgavran/Category_Theory_Machine_Learning

What it solves

This project addresses the need for a centralized, organized collection of research papers that apply category theory to machine learning. It helps researchers and students navigate the growing intersection of these two fields by categorizing complex academic literature into manageable topics.

How it works

The repository acts as a curated bibliography. It groups academic papers, theses, and blog posts into specific sub-fields such as deep learning, probability theory, graph neural networks, and Bayesian inference. It provides direct links to the original research papers, allowing users to explore the mathematical foundations of various machine learning architectures and algorithms.

Who it’s for

This resource is designed for researchers, mathematicians, and machine learning practitioners interested in the theoretical underpinnings of AI. It is particularly useful for those looking to understand how categorical structures can formalize concepts like neural network architectures, automatic differentiation, and learning dynamics.

Highlights

• Comprehensive list of academic papers, theses, and blog posts.
• Organized by specific domains like Equivariance, Reinforcement Learning, and Topological Data Analysis.
• Includes foundational resources for those new to category theory.
• Community-driven, allowing for contributions via pull requests to keep the list updated.