no code implementations • 8 Nov 2022 • Lucas Hayne, Abhijit Suresh, Hunar Jain, Rahul Kumar, R. McKell Carter
More specifically, we find that an interaction between selectivity and the average activity of the unit better predicts ablation performance deficits for groups of units in AlexNet, VGG16, MobileNetV2, and ResNet101.
1 code implementation • 25 Jul 2022 • Charles Edison Tripp, Jordan Perr-Sauer, Lucas Hayne, Monte Lunacek, Jamil Gafur
We present an empirical dataset surveying the deep learning phenomenon on fully-connected feed-forward multilayer perceptron neural networks.
