3 citations · 3 across the 1 of their papers we have counts for
2 papers
cs.NE2020
Learn Faster and Forget Slower via Fast and Stable Task Adaptation
Farshid Varno, Lucas May Petry, Lisa Di Jorio +1
Training Deep Neural Networks (DNNs) is still highly time-consuming and compute-intensive. It has been shown that adapting a pretrained model may significantly accelerate this proc…
cs.LG2019★ 3 cited
Efficient Neural Task Adaptation by Maximum Entropy Initialization
Farshid Varno, Behrouz Haji Soleimani, Marzie Saghayi +2
Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potential…