AINeutralarXiv – CS AI · 9h ago6/10
🧠
A Generalized Singular Value Theory for Neural Networks
Researchers prove that modern neural networks can be represented using a Generalized Singular Value Decomposition that makes them left-invertible before a final linear layer while preserving norm properties. This mathematical framework enables distance calibration between feature space and input space, with demonstrated applications to adversarial perturbation detection and potential future use in addressing model bias and invertibility.