Learning constraints from natural images
(Yee-Whye Teh)
•We used 16x16 image patches and a single layer of 768 hidden units (3 x overcomplete).
•
•Confabulations are produced from data by adding random momentum once and simulating dynamics for 30 steps.
•
•Weights are updated every 100 examples.
•
•A small amount of weight decay helps.