1 code implementation • journal 2023 • Chuan Qin, Liangming Chen, Zangtai Cai, Mei Liu, Long Jin
As the number of long short-term memory (LSTM) layers increases, vanishing/exploding gradient problems exacerbate and have a negative impact on the performance of the LSTM.
1 code implementation • 27 Jun 2022 • Liangming Chen, Long Jin, Mingsheng Shang
We first give the interpretation of zero stability in the context of deep learning and then investigate the performance of existing first- and second-order CNNs under different zero-stable circumstances.
2 code implementations • 9 Jul 2021 • Mei Liu, Liangming Chen, Xiaohao Du, Long Jin, Mingsheng Shang
The experimental results also demonstrate that the proposed method is able to be adopted in various deep neural networks to improve their performance.
no code implementations • 14 Sep 2020 • Liangming Chen, Long Jin, Xiujuan Du, Shuai Li, Mei Liu
With visualizations of loss landscapes, we evaluate the flatnesses of minima obtained by both the original optimizer and optimizers enhanced by VDMs on CIFAR-100.
no code implementations • 24 Jul 2020 • Liangming Chen, Long Jin, Xiujuan Du, Shuai Li, Mei Liu
Furthermore, the flatter minima could be obtained by exploiting the proposed deformation functions, which is verified on CIFAR-100, with visualizations of loss landscapes near the critical points obtained by both the original optimizer and optimizer enhanced by deformation functions.