Unambiguous Representations in Neural Networks: An Information-Theoretic Approach to Intentionality
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915670682238976 |
|---|---|
| author | Lässig, Francesco |
| author_facet | Lässig, Francesco |
| contents | Representations pervade our daily experience, from letters representing sounds to bit strings encoding digital files. While such representations require externally defined decoders to convey meaning, conscious experience appears fundamentally different: a neural state corresponding to perceiving a red square cannot alternatively encode the experience of a green square. This intrinsic property of consciousness suggests that conscious representations must be unambiguous in a way that conventional representations are not. We formalize this intuition using information theory, defining representational ambiguity as the conditional entropy H(I|R) over possible interpretations I given a representation R. Through experiments on neural networks trained to classify MNIST digits, we demonstrate that relational structures in network connectivity can unambiguously encode representational content. Using both learned decoders and direct geometric matching, we achieve perfect (100%) accuracy for dropout-trained networks and 38% for standard backpropagation in identifying output neuron class identity, despite identical task performance, demonstrating that representational ambiguity can arise orthogonally to behavioral accuracy. We further show that spatial position information of input neurons can be decoded from network connectivity with R2 up to 0.844. These results provide a quantitative method for measuring representational ambiguity in neural systems and demonstrate that neural networks can exhibit the low-ambiguity representations posited as necessary (though not sufficient) by theoretical accounts of consciousness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11000 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unambiguous Representations in Neural Networks: An Information-Theoretic Approach to Intentionality Lässig, Francesco Neurons and Cognition Artificial Intelligence Neural and Evolutionary Computing Representations pervade our daily experience, from letters representing sounds to bit strings encoding digital files. While such representations require externally defined decoders to convey meaning, conscious experience appears fundamentally different: a neural state corresponding to perceiving a red square cannot alternatively encode the experience of a green square. This intrinsic property of consciousness suggests that conscious representations must be unambiguous in a way that conventional representations are not. We formalize this intuition using information theory, defining representational ambiguity as the conditional entropy H(I|R) over possible interpretations I given a representation R. Through experiments on neural networks trained to classify MNIST digits, we demonstrate that relational structures in network connectivity can unambiguously encode representational content. Using both learned decoders and direct geometric matching, we achieve perfect (100%) accuracy for dropout-trained networks and 38% for standard backpropagation in identifying output neuron class identity, despite identical task performance, demonstrating that representational ambiguity can arise orthogonally to behavioral accuracy. We further show that spatial position information of input neurons can be decoded from network connectivity with R2 up to 0.844. These results provide a quantitative method for measuring representational ambiguity in neural systems and demonstrate that neural networks can exhibit the low-ambiguity representations posited as necessary (though not sufficient) by theoretical accounts of consciousness. |
| title | Unambiguous Representations in Neural Networks: An Information-Theoretic Approach to Intentionality |
| topic | Neurons and Cognition Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2512.11000 |