Results on modeling natural image patches using a stack of RBM’s (Osindero and Hinton)
		• 100,000 Van Hateren image patches, each 20x20 • Stack of RBM’s learned one at a time. • 400 Gaussian visible units that see whitened image patches. • 40020005001000 • Hidden units are all binary with learned lateral connections when they are the visible units of their RBM. • Generation involves letting the visible units of each RBM settle using mean field with the already decided states in the level above determining the effective biases.