Experiment 1: Learning Sparse FRAME by Generative Boosting with Local Normalization
back to page
data
Typical parameters:
image size is 100x100. The number of basis functions is 700. The allowed range of perturbation in location is 2 pixels. The allowed range of perturbation in rotation is pi/16.
GaborScaleList=[ 1.4, 1,0.7,0.5]. DoGScaleList =[18.90,13.36]. interval=3. 10x10 chains.
threshold_corrBB = 0; lower_bound_rand = 0.001; upper_bound_rand = 0.999;c_val_list=-25:2:25. isLocalNormalize=true; isSeparate=false; thresholdFactor=0.01; localNormScaleFactor=2.