Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> This is part of why deep learning and tensor methods work so well on image classification tasks.

That statement sounds informative. Do you have a good non-specialist's reference?



You might be interested by colah's (Christopher Olah's) blog: https://colah.github.io/

Two articles in particular are good introductions to looking at neural networks in terms of higher dimensional data lying on lower-dimesnional manifolds:

Neural Networks, Manifolds, and Topology: https://colah.github.io/posts/2014-03-NN-Manifolds-Topology/

Visualizing MNIST: An Exploration of Dimensionality Reduction: https://colah.github.io/posts/2014-10-Visualizing-MNIST/


Thank you for the useful links.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: