Written by
Sanghyuk Kim
on
on
Paper Accepted in Neurocomputing

I am pleased to share that our paper has been accepted for publication in Neurocomputing.
Kim S, Kim H*, Kang N, Lee TH* (2025) Projected variable three-term conjugate gradient algorithm for enhancing generalization performance in deep neural network training. Neurocomputing, 131568. https://doi.org/10.1016/j.neucom.2025.131568
This work proposes the Projected Variable Three-Term Conjugate Gradient (PVTTCG) algorithm, which effectively balances fast convergence and improved generalization in deep learning, with validation across image classification, language modeling, and real-world engineering applications.