The objective is to implement some outlier detection strategies. More description in outlier-detection.pdf
Using PCA + Robust PCA
RNN (replicator neural network) : the input variables are also the output variables so that the RNN forms an implicit, compressed model of the data during training. The RNN approach has linear analogues in Principal Components Analysis.
The work is based on the paper "Outlier Detection Using Replicator Neural Network" Simon Hawkins, Hongxing He, Graham Williams and Rohan Baxter http://neuro.bstu.by/ai/To-dom/My_research/Papers-0/For-research/D-mining/Anomaly-D/KDD-cup-99/NN/dawak02.pdf