We consider functions defined by deep neural networks as definable objects in an o-miminal expansion of the real field, and derive an almost linear (in the number of weights) bound on sample complexity of such networks.
Net-Trim: A Layer-wise Convex Pruning of Deep Neural Networks
Weight Initialization of Deep Neural Networks(DNNs) using Data Statistics
A unified view of gradient-based attribution methods for Deep Neural Networks
![QR code for arXiv:1910.11080 [cs.LG]](http://oss.arxitics.com/images/favicon.svg)