8 citations · 16 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 8 cited
Automated Sizing and Training of Efficient Deep Autoencoders using Second Order Algorithms
Kanishka Tyagi, Chinmay Rane, Michael Manry
We propose a multi-step training method for designing generalized linear classifiers. First, an initial multi-class linear classifier is found through regression. Then validation e…
cs.LG2023★ 8 cited
Optimal Input Gain: All You Need to Supercharge a Feed-Forward Neural Network
Chinmay Rane, Kanishka Tyagi, Sanjeev Malalur +2
Linear transformation of the inputs alters the training performance of feed-forward networks that are otherwise equivalent. However, most linear transforms are viewed as a pre-proc…