Showing cs.LGShow all
3 papers · 1 filter
cs.LG2024
Harmonic Machine Learning Models are Robust
Nicholas S. Kersting, Yi Li, Aman Mohanty +2
We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference mo…
cs.LG2024
Harmonic LLMs are Trustworthy
Nicholas S. Kersting, Mohammad Rahman, Suchismitha Vedala +1
We introduce an intuitive method to test the robustness (stability and explainability) of any black-box LLM in real-time via its local deviation from harmoniticity, denoted as .…
cs.LG2023
ONNXExplainer: an ONNX Based Generic Framework to Explain Neural Networks Using Shapley Values
Yong Zhao, Runxin He, Nicholas Kersting +4
Understanding why a neural network model makes certain decisions can be as important as the inference performance. Various methods have been proposed to help practitioners explain…