Does the Brain Infer Invariance Transformations from Graph Symmetries?
This work addresses the fundamental problem of how the brain achieves perceptual invariance, which is crucial for understanding neural computation and AI, but it is incremental as it builds on existing symmetry and graph theory concepts.
The paper investigates whether the brain encodes invariance to perceptual changes through symmetries in synaptic connection graphs, proposing that this encoding arises from unsupervised learning across modalities and is supported by correlations in natural data, predicting neural connectivity consistent with sensory cortex observations.
The invariance of natural objects under perceptual changes is possibly encoded in the brain by symmetries in the graph of synaptic connections. The graph can be established via unsupervised learning in a biologically plausible process across different perceptual modalities. This hypothetical encoding scheme is supported by the correlation structure of naturalistic audio and image data and it predicts a neural connectivity architecture which is consistent with many empirical observations about primary sensory cortex.