2 papers
cs.LG2022
Much Easier Said Than Done: Falsifying the Causal Relevance of Linear Decoding Methods
Lucas Hayne, Abhijit Suresh, Hunar Jain +2
Linear classifier probes are frequently utilized to better understand how neural networks function. Researchers have approached the problem of determining unit importance in neural…
cs.LG2022
The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks
Charles Edison Tripp, Jordan Perr-Sauer, Lucas Hayne +2
We present an empirical dataset surveying the deep learning phenomenon on fully-connected feed-forward multilayer perceptron neural networks. The dataset, which is now freely avail…