LGDec 12, 2024
Neural Network Symmetrisation in Concrete Settings
arXiv:2412.09469v1h-index: 2
Originality Synthesis-oriented
AI Analysis
This work is incremental, as it reviews and applies existing theoretical results to specific contexts without introducing new methods or data.
The paper provides a high-level overview of Cornish's (2024) general theory of neural network symmetrisation in Markov categories, focusing on its concrete implications for symmetrising deterministic functions and Markov kernels.
Cornish (2024) recently gave a general theory of neural network symmetrisation in the abstract context of Markov categories. We give a high-level overview of these results, and their concrete implications for the symmetrisation of deterministic functions and of Markov kernels.