Qiang Ye

Stochastic Gradient Descent with Nonlinear Conjugate Gradient-Style Adaptive Momentum

2020 · arXiv (Cornell University)

Momentum plays a crucial role in stochastic gradient-based optimization algorithms for accelerating or improving training deep neural networks (DNNs). In deep learning practice, the momentum is usually weighted by a well-calibrated constant. However, tuning hyperparameters …

Substation Project Evaluation Model Based on Coefficient of Variation And Fuzzy Comprehensive Evaluation

2022 · 2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)

Aiming at the problems of single traditional index, fuzzy evaluation result and subjective index weight in evaluating the investment benefit of substation project, a substation project evaluation model based on coefficient of variation and fuzzy …