no code implementations • 11 Nov 2022 • Yi Ren, Yanyang Xiao, Guo-Qiang Bi, Pek-Ming Lau
With these understandings, we developed a STDP based learning rule which could drive the network to remember any presupposed sequence.
3 code implementations • 19 Jan 2019 • Zhi-Qin John Xu, Yaoyu Zhang, Tao Luo, Yanyang Xiao, Zheng Ma
We study the training process of Deep Neural Networks (DNNs) from the Fourier analysis perspective.
1 code implementation • 3 Jul 2018 • Zhi-Qin John Xu, Yaoyu Zhang, Yanyang Xiao
Why deep neural networks (DNNs) capable of overfitting often generalize well in practice is a mystery [#zhang2016understanding].