Neuronal Firing Rate As Code Length: a Hypothesis

Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers

Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the Minimum Description Length (MDL) principle. Treating the neural network optimization process as a partially observable model selection problem, the regularity normalization constrains the implicit space by a normalization factor, the universal code length. We compute this universal code incrementally across neural network layers and demonstrate the flexibility to include data priors such as top-down attention and other oracle information. Empirically, our approach outperforms existing normalization methods in tackling limited, imbalanced and non-stationary input distribution in image classification, classic control, procedurally-generated reinforcement learning, generative modeling, handwriting generation and question answering tasks with various neural network architectures. Lastly, the unsupervised attention mechanisms is a useful probing tool for neural networks by tracking the dependency and critical learning stages across layers and recurrent time steps of deep networks.

From likely to likable: The role of statistical typicality in human social assessment of faces

Humans readily form social impressions, such as attractiveness and trustworthiness, from a stranger's facial features. Understanding the provenance of these impressions has clear scientific importance and societal implications. Motivated by the efficient coding hypothesis of brain representation, as well as Claude Shannon's theoretical result that maximally efficient representational systems assign shorter codes to statistically more typical data (quantified as log likelihood), we suggest that social "liking" of faces increases with statistical typicality. Combining human behavioral data and computational modeling, we show that perceived attractiveness, trustworthiness, dominance, and valence of a face image linearly increase with its statistical typicality (log likelihood). We also show that statistical typicality can at least partially explain the role of symmetry in attractiveness perception. Additionally, by assuming that the brain focuses on a task-relevant subset of facial features and assessing log likelihood of a face using those features, our model can explain the "ugliness-in-averageness" effect found in social psychology, whereby otherwise attractive, intercategory faces diminish in attractiveness during a categorization task.

Our understanding of neural codes rests on Shannon's foundations

Shannon's theory lays the foundation for understanding the flow of information from world into brain: There must be a set of possible messages. Brain structure determines what they are. Many messages convey quantitative facts (distances, directions, durations, etc.). It is impossible to consider how neural tissue processes these numbers without first considering how it encodes them.