Discovering sensor space: Constructing spatial embeddings that explain sensor correlations

A fundamental task for a developing agent is to build models that explain its uninterpreted sensory-motor experience. This paper describes an algorithm that constructs a sensor space from sensor correlations, namely the algorithm generates a spatial embedding of sensors where strongly correlated sensors will be neighbors in the embedding. The algorithm first infers a sensor correlation distance and then applies the fast maximum variance unfolding algorithm to generate a distance preserving embedding. Although previous work has shown how sensor embeddings can be constructed, this paper provides a framework for understanding sensor embedding, introduces a sensor correlation distance, and demonstrates embeddings for thousands of sensors on intrinsically curved manifolds.