# Bridging Philosophy and Machine Learning: A Structuralist Framework for Classifying Neural Network Representations

arXiv: https://arxiv.org/abs/2511.18633 · HTML: https://mlsanity.com/paper/2511.18633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 23 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Explainability in Deep Reinforcement Learning](https://mlsanity.com/paper/2008.06693/) (2020)
- [Ontology Reasoning with Deep Neural Networks](https://mlsanity.com/paper/1808.07980/) (2018)
- [Machine Learning and the Future of Realism](https://mlsanity.com/paper/1704.04688/) (2017)

## Abstract (arXiv)

Machine learning models increasingly function as representational systems, yet the philosoph- ical assumptions underlying their internal structures remain largely unexamined. This paper develops a structuralist decision framework for classifying the implicit ontological commitments made in machine learning research on neural network representations. Using a modified PRISMA protocol, a systematic review of the last two decades of literature on representation learning and interpretability is conducted. Five influential papers are analysed through three hierarchical criteria derived from structuralist philosophy of science: entity elimination, source of structure, and mode of existence. The results reveal a pronounced tendency toward structural idealism, where learned representations are treated as model-dependent constructions shaped by architec- ture, data priors, and training dynamics. Eliminative and non-eliminative structuralist stances appear selectively, while structural realism is notably absent. The proposed framework clarifies conceptual tensions in debates on interpretability, emergence, and epistemic trust in machine learning, and offers a rigorous foundation for future interdisciplinary work between philosophy of science and machine learning.