Parallel Algorithms for Exact Enumeration of Deep Neural Network Activation Regions

arXiv:2403.00860v1 Announce Type: new
Abstract: A feedforward neural network using rectified linear units constructs a mapping from inputs to outputs by partitioning its input space into a set of convex regions where points within a region share a single affine transformation. In order to understand how neural networks work, when and why they fail, and how they compare to biological intelligence, we need to understand the organization and formation of these regions. Step one is to design and implement algorithms …

abstract algorithms arxiv cs.ai cs.lg cs.ne deep neural network inputs linear mapping network networks neural network neural networks partitioning set space transformation type units work