ReLU code space: A basis for rating network quality besides accuracy
Michal Mariusz Lewandowski
Bernhard A. Moser
|Titel||ReLU code space: A basis for rating network quality besides accuracy|
|Buchtitel||Machine Learning (strat.ML), https://arxiv.org/abs/2005.09903|
|Organisation||Published as a conference paper at NAS 2020 - 1st ICLR Workshop on Neural Architecture Search, Addis Ababa, Ethiopia, April 26, 2020 collocated with ICLR 2020 - 8th International Conference on Learning Representations, Addis Ababa, Ethiopia, April 26-30,|
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.