Algorithmic Probability-Guided Machine Learning on Non-Differentiable Spaces.

ABSTRACT: We show how complexity theory can be introduced in machine learning to help bring together apparently disparate areas of current research. We show that this model-driven approach may require less training data and can potentially be more generalizable as it shows greater resilience to random attacks. In an algorithmic space the order of its element is given by its algorithmic probability, which arises naturally from computable processes. We investigate the shape of a discrete algorithmic space when performing regression or classification using a loss function parametrized by algorithmic complexity, demonstrating that the property of differentiation is not required to achieve results similar to those obtained using differentiable programming approaches such as deep learning. In doing so we

SUBMITTER: Hernandez-Orozco S 

PROVIDER: S-EPMC7944352 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature