Digital implementations of deep feature extractors are intrinsically informative

Both cri teria are related by the key component of information retention, which leaves feature engineers with the challenging task of balancing the discriminative power of the feature extracto r (i.e., the ability to disentangle the driving factors for va riance within the data) and the potential loss of information (as a result of transforming the input). In this contribution, we focus on the premise that deep feature extractors should contain m ost of the (relevant) information about their input signals, wh ich is expressed by the aggregate energy content of the features . A. Prior work Information retention is a key component of successful feature extraction. It has hence already been addressed by prior works--mainly in the context of scattering CNNs, both over Euclidean domains [5]-[10] and graphs [11], [12].