no code implementations • 27 Apr 2024 • Michael Majurski, Sumeet Menon, Parniyan Farvardin, David Chapman
To address this we introduce a novel embedding constraint based on the Method of Moments (MoM).
no code implementations • 12 Dec 2022 • Peter Bajcsy, Antonio Cardone, Chenyi Ling, Philippe Dessauw, Michael Majurski, Tim Blattner, Derek Juba, Walid Keyrouz
We approach the problems by introducing theoretical underpinnings of AI model utilization measurement and understanding patterns in utilization-based class encodings of traffic signs at the level of computation graphs (AI models), subgraphs, and graph nodes.
2 code implementations • 22 Jan 2021 • Peter Bajcsy, Michael Majurski
Next, measure the accuracy of a set of systematically pruned NN models following multiple pruning schemas.
1 code implementation • 5 Jun 2020 • Peter Bajcsy, Nicholas J. Schaub, Michael Majurski
This work presents a web-based interactive neural network (NN) calculator and a NN inefficiency measurement that has been investigated for the purpose of detecting trojans embedded in NN models.