Poster
in
Workshop: Symmetry and Geometry in Neural Representations
A minimalistic representation model for head direction system
Minglu Zhao · Dehong Xu · Deqian Kong · Wenhao Zhang · Ying Nian Wu
Keywords: [ U(1) rotation symmetry group ] [ Recurrent neural network ] [ Path integration ] [ Group representation ]
Abstract:
We present a minimalistic representation model for the head direction (HD) system, aiming to learn a high-dimensional representation of head direction that captures essential properties of HD cells. Our model is a representation of rotation group $U(1)$, and we study both the fully connected version and convolutional version. We demonstrate the emergence of Gaussian-like tuning profiles and a 2D circle geometry in both versions of the model. We also demonstrate that the learned model is capable of accurate path integration.
Chat is not available.