3 citations · 4 across the 2 of their papers we have counts for
2 papers
cs.NE2024★ 1 cited
Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks
Takuro Kutsuna
In this paper, we first identify activation shift, a simple but remarkable phenomenon in a neural network in which the preactivation value of a neuron has non-zero mean that depend…
cs.LG2023★ 3 cited
Supervised Contrastive Learning with Heterogeneous Similarity for Distribution Shifts
Takuro Kutsuna
Distribution shifts are problems where the distribution of data changes between training and testing, which can significantly degrade the performance of a model deployed in the rea…