Unambiguous Representations in Neural Networks: An Information-Theoretic Approach to Intentionality

TL;DR

This paper introduces an information-theoretic framework to quantify representational ambiguity in neural networks, demonstrating that unambiguous, consciousness-like representations can be encoded through network connectivity structures.

Contribution

It formalizes the concept of representational ambiguity using conditional entropy and shows how neural networks can achieve low-ambiguity representations through specific connectivity patterns.

Findings

Perfect decoding accuracy in dropout-trained networks

Lower decoding accuracy in standard backpropagation networks

High correlation (R2 up to 0.844) between connectivity and spatial input position

Abstract

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.