Bridging Philosophy and Machine Learning: A Structuralist Framework for Classifying Neural Network Representations
This work addresses conceptual tensions in interpretability and trust for machine learning researchers, but it is incremental as it applies existing philosophical ideas to a new domain.
The paper tackles the problem of unexamined philosophical assumptions in neural network representations by developing a structuralist framework to classify ontological commitments, revealing a tendency toward structural idealism and the absence of structural realism in the literature.
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.