A Group Theoretic Analysis of the Symmetries Underlying Base Addition and Their Learnability by Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911058712592384 |
|---|---|
| author | Dawes, Cutter Segert, Simon Krishnamurthy, Kamesh Cohen, Jonathan D. |
| author_facet | Dawes, Cutter Segert, Simon Krishnamurthy, Kamesh Cohen, Jonathan D. |
| contents | A major challenge in the use of neural networks both for modeling human cognitive function and for artificial intelligence is the design of systems with the capacity to efficiently learn functions that support radical generalization. At the roots of this is the capacity to discover and implement symmetry functions. In this paper, we investigate a paradigmatic example of radical generalization through the use of symmetry: base addition. We present a group theoretic analysis of base addition, a fundamental and defining characteristic of which is the carry function -- the transfer of the remainder, when a sum exceeds the base modulus, to the next significant place. Our analysis exposes a range of alternative carry functions for a given base, and we introduce quantitative measures to characterize these. We then exploit differences in carry functions to probe the inductive biases of neural networks in symmetry learning, by training neural networks to carry out base addition using different carries, and comparing efficacy and rate of learning as a function of their structure. We find that even simple neural networks can achieve radical generalization with the right input format and carry function, and that learnability is closely correlated with carry function structure. We then discuss the relevance this has for cognitive science and machine learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10678 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Group Theoretic Analysis of the Symmetries Underlying Base Addition and Their Learnability by Neural Networks Dawes, Cutter Segert, Simon Krishnamurthy, Kamesh Cohen, Jonathan D. Machine Learning Artificial Intelligence Neural and Evolutionary Computing Neurons and Cognition A major challenge in the use of neural networks both for modeling human cognitive function and for artificial intelligence is the design of systems with the capacity to efficiently learn functions that support radical generalization. At the roots of this is the capacity to discover and implement symmetry functions. In this paper, we investigate a paradigmatic example of radical generalization through the use of symmetry: base addition. We present a group theoretic analysis of base addition, a fundamental and defining characteristic of which is the carry function -- the transfer of the remainder, when a sum exceeds the base modulus, to the next significant place. Our analysis exposes a range of alternative carry functions for a given base, and we introduce quantitative measures to characterize these. We then exploit differences in carry functions to probe the inductive biases of neural networks in symmetry learning, by training neural networks to carry out base addition using different carries, and comparing efficacy and rate of learning as a function of their structure. We find that even simple neural networks can achieve radical generalization with the right input format and carry function, and that learnability is closely correlated with carry function structure. We then discuss the relevance this has for cognitive science and machine learning. |
| title | A Group Theoretic Analysis of the Symmetries Underlying Base Addition and Their Learnability by Neural Networks |
| topic | Machine Learning Artificial Intelligence Neural and Evolutionary Computing Neurons and Cognition |
| url | https://arxiv.org/abs/2507.10678 |