Re:Machine learning works spectacularly well, but mathematic...
by chestervonwinch on Friday December 04, 2015 @03:34PM
(#10678955)
There are diffusion based methods for unsupervised learning based on the graph laplacian, or heat kernel [0]. Maybe this is what she was referring to? I would guess so, because Coifman (who is also closely tied to wavelets [1]) introduced the diffusion maps [2] method. On the other hand, I have not seen any unsupervised method based on say, Navier-Stokes, which is the only other thing that comes to mind for regarding ink drops diffusing.
[0]: http://www.mit.edu/~9.520/spring11/slides/class20_misha.pdf
Re:Machine learning works spectacularly well, but mathematic...
by jeremysalwen on Saturday December 05, 2015 @02:10AM
(#10681177)
This reminded me of this paper on using deep autoencoders as a generative model: http://papers.nips.cc/paper/5023-generalized-denoising-auto-... I don't think it's exactly a right analogy, but there's something there about the local flow of MCMC locally describing the manifold structure, and thus generating it globally.
It sounds to me like this 'ink drop' is a metaphor to explain some state-of-the-art dimensionality reduction technique. Does anyone know the common name of this technique?