Local Explanation Method using Nonlinear Approximation(LEMNA)
Implementation of the research paper Guo, Wenbo, et al. "Lemna: Explaining deep learning based security applications." Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security. ACM, 2018.
- Generates a small set of interpretable features to explain how the input sample is classified by the neural network
- Boosts the explanation fidelity by approximating the local area of the complex deep learning decision boundary