9 citations · 9 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Unveiling the Training Dynamics of ReLU Networks through a Linear Lens
Longqing Ye
Deep neural networks, particularly those employing Rectified Linear Units (ReLU), are often perceived as complex, high-dimensional, non-linear systems. This complexity poses a sign…
cs.LG2022
AugOp: Inject Transformation into Neural Operator
Longqing Ye
In this paper, we propose a simple and general approach to augment regular convolution operator by injecting extra group-wise transformation during training and recover it during i…