I try to use Hessian-free optimization to train the deep neural network. The training is based on the MNIST data set.
-
Updated
Nov 27, 2014 - MATLAB
I try to use Hessian-free optimization to train the deep neural network. The training is based on the MNIST data set.
Second order information based SGD
Final seminar for the Logic for CS class.
Ph.D. thesis of Jared Corduan - Coloring Posets and Reverse Mathematics
How much infinity does physics need? Fekete lemma, c-function IR limits, Cantor scaling exponents and limit-set connectivity are each equivalent to ACA0 over RCA0; computable moduli vs uncomputable limits and the empirical boundary (Paper 10)
To associate your repository with the second-order-arithmetic topic, visit your repo's landing page and select "manage topics."