ReLU Code Space: A Basis for Rating Network Quality Besides Accuracy
Natalia Shepeleva, Werner Zellinger, Michal Lewandowski, Bernhard, Moser

TL;DR
This paper introduces a novel ReLU code space with a truncated Hamming distance that correlates network activation patterns with safety and robustness, enabling new insights beyond accuracy.
Contribution
It establishes an isometry between activation codes and input space regions, facilitating analysis of network robustness and confidence.
Findings
Code space relates to safety and robustness
Efficient adjacency computation between input regions
Information beyond accuracy is stored in codes
Abstract
We propose a new metric space of ReLU activation codes equipped with a truncated Hamming distance which establishes an isometry between its elements and polyhedral bodies in the input space which have recently been shown to be strongly related to safety, robustness, and confidence. This isometry allows the efficient computation of adjacency relations between the polyhedral bodies. Experiments on MNIST and CIFAR-10 indicate that information besides accuracy might be stored in the code space.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSemiconductor materials and devices · VLSI and Analog Circuit Testing · Advanced Memory and Neural Computing
Methods*Communicated@Fast*How Do I Communicate to Expedia?
