projects:asgd:start
Differences
This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
projects:asgd:start [2015/02/11 17:09] – created hj | projects:asgd:start [2015/07/12 14:04] (current) – hj | ||
---|---|---|---|
Line 1: | Line 1: | ||
====== Annealing SGD ====== | ====== Annealing SGD ====== | ||
- | ===== Annealing | + | ===== Annealed |
- | {{ : | + | {{ : |
+ | \\ | ||
+ | \\ | ||
+ | Here, we propose a novel annealed gradient descent (AGD) method for | ||
+ | deep learning. AGD optimizes a sequence of gradually improved smoother mosaic | ||
+ | functions that approximate the original non-convex objective function according | ||
+ | to an annealing schedule during optimization process. We present a theoretical | ||
+ | analysis on its convergence properties and learning speed. The proposed AGD | ||
+ | algorithm is applied to learning deep neural networks (DNN) for image recognition | ||
+ | in MNIST and speech recognition in Switchboard. | ||
+ | \\ | ||
+ | **Reference: | ||
+ | |||
+ | [1] //Hengyue Pan, Hui Jiang//, " |
projects/asgd/start.1423674565.txt.gz · Last modified: 2015/02/11 17:09 by hj