Γ-stochastic neighbour embedding for feed-forward data visualization

Abstract

t-distributed Stochastic Neighbour Embedding (t-SNE) is one of the most popular nonlinear dimension reduction techniques used in multiple application domains. In this paper we propose a variation on the embedding neighbourhood distribution, resulting in Γ-SNE, which can construct a feed-forward mapping using an RBF network. We compare the visualizations generated by Γ-SNE with those of t-SNE and provide empirical evidence suggesting the network is capable of robust interpolation and automatic weight regularization.