Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021
When saliency goes off on a tangent: Interpreting Deep Neural Networks with nonlinear saliency maps
Jan Rosenzweig, Zoran Cvetkovic, Ivana Rosenzweig
A fundamental bottleneck in utilising complex machine learning systems for critical applications has been not knowing why they do and what they do, thus preventing the development…
cs.LG2020
Goldilocks Neural Networks
Jan Rosenzweig, Zoran Cvetkovic, Ivana Rosenzweig
We introduce the new "Goldilocks" class of activation functions, which non-linearly deform the input signal only locally when the input signal is in the appropriate range. The smal…