Empirical Evaluation of Whitening and Optimization of Feature Learning

Deep learning and Feature learning emerged new field in machine learning and beat many, state of the arts results in diverse areas. Well established feature learning Sparse-Auto encoder was chosen in our work and tunes their different critical parameters. We have shown that tweaking right parameter can improved results and good features can be obtained. Different Whitening preprocessing techniques and optimization methods were applied on well known data set corel-100 and found out that Cost effective PCA whitening is also same reliable as cost prone other whitening techniques. Different Optimization methods were analyzed and experiments show L-BFGS beat CG as data goes large.