A Comparison Study on Rule Extraction from Neural Network Ensembles, Boosted Shallow Trees, and SVMs

<div>A QSVM network with Gaussian kernel. The first hidden layer performs a quantized normalization of the inputs, while the incoming weights into neurons of the second hidden layer represent support vectors.</div>

Applied Computational Intelligence and Soft Computing

fig3

Figure 3

Figure 3: A Comparison Study on Rule Extraction from Neural Network Ensembles, Boosted Shallow Trees, and SVMs 