t-Distributed stochastic neighbour embedding is one of the most popular non-linear dimension-reduction techniques used in multiple application domains. In this article, we propose a variation on the embedding neighbourhood distribution, resulting in Γ-stochastic neighbour embedding, which can construct a feed-forward mapping using a radial basis function network. We compare the visualizations generated by Γ-stochastic neighbour embedding with those of t-distributed stochastic neighbour embedding and provide empirical evidence suggesting the network is capable of robust interpolation and automatic weight regularization.
GraciaAGonzálezSRoblesV. New insights into the suitability of the third dimension for visualizing multivariate/multidimensional data: a study based on loss of quality quantification. Inform Visual2016; 15(1): 3–30, http://ivi.sagepub.com/content/15/1/3.abstract
Van der MaatenLPostmaEVan den HerikJ. Dimensionality reduction: a comparative review. J Mach Learn Res2009; 10: 1–41.
5.
RoweisSTSaulLK.Nonlinear dimensionality reduction by locally linear embedding. Science2000; 290: 2323–2326.
6.
HintonGERoweisST.Stochastic neighbor embedding. In: JordanM (ed.) Advances in neural information processing systems. Cambridge, MA: The MIT Press2002, pp. 833–840.
7.
LoweDTippingME.NeuroScale: novel topographic feature extraction using RBF networks. In: MozerMJordanMPetscheT (eds) Advances in neural information processing systems 9. Cambridge, MA: The MIT Press, 1997, pp. 543–549.
8.
RiceI.Probabilistic topographic information visualisation. PhD Thesis, Aston University, Birmingham, 2015.
9.
Van der MaatenLJPHintonGE. Visualizing high-dimensional data using t-SNE. JLMR2008; 9: 2579–2605.
Van der MaatenL. Learning a parametric embedding by preserving local structure. In: DykDAVWellingM (eds) Proceedings of the twelfth international conference on artificial intelligence and statistics AISTATS 2009 (Journal of Machine Learning Research - Proceedings Track, vol. 5). JMLR, pp. 384–391, http://jmlr.csail.mit.edu/proceedings/papers/v5/maaten09a/maaten09a.pdf
14.
BunteKHaaseSBiehlM. Stochastic neighbor embedding (SNE) for dimension reduction and visualization using arbitrary divergences. Neurocomputing2012; 90: 23–45, http://dx.doi.org/10.1016/j.neucom.2012.02.034
15.
DikmenOYangZOjaE.Learning the information divergence. IEEE T Pattern Anal2015; 37(7): 1442–1454.
16.
ChernoffH.A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Ann Math Stat1952; 23(4): 493–507.
17.
FujisawaHEguchiS.Robust parameter estimation with a small bias against heavy contamination. J Multivariate Anal2008; 99(9): 2053–2081.
TippingMELoweD.Shadow targets: a novel algorithm for topographic projections by radial basis functions. Neurocomputing1997; 19: 211–222.
20.
TippingME.Topographic mappings and feed-forward neural networks. PhD Thesis, Aston University, Birmingham, 1996.
21.
LinTZhaHLeeS.Riemannian manifold learning for nonlinear dimensionality reduction. In: LeonardisABischofHPinzA (eds) Proceedings of the 9th European conference on computer vision: Volume Part I. ECCV’06. Berlin, Heidelberg: Springer, 2006, pp. 44–55.
DamianouACLawrenceND.Deep Gaussian processes. In: Proceedings of the sixteenth international conference on artificial intelligence and statistics, AISTATS 2013, Scottsdale, AZ, 29 April–1 May 2013. pp. 207–215, http://jmlr.org/proceedings/papers/v31/damianou13a.html
24.
Fei-FeiLFergusRPeronaP. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Computer Vision and Image Understanding2001; 106: 59–70, http://dx.doi.org/10.1016/j.cviu.2005.09.012.
25.
BayHTuytelaarsTGoolL.SURF: Speeded up robust features. In: LeonardisABischofHPinzA (eds) Computer Vision – ECCV 2006: 9th European conference on computer vision, Graz, Austria, May 7–13, 2006. Proceedings, part I. Berlin, Heidelberg: Springer, 2006, pp. 404–417.
26.
RiceI.Improved data visualisation through multiple dissimilarity modelling. Inform Sciences2016; 370–371: 288–302.
ElzbietaPDuinRPW. The dissimilarity representation for pattern recognition: foundations and applications (machine perception and artificial intelligence). River Edge, NJ: World Scientific Publishing Co. Inc., 2005.
