Deep frequency principle towards understanding why deeper learning is faster ZJ Xu, H Zhou Proceedings of the AAAI Conference on Artificial Intelligence 35 (12), 10541 …, 2021 | 27 | 2021 |
Empirical phase diagram for three-layer neural networks with infinite width H Zhou, Z Qixuan, Z Jin, T Luo, Y Zhang, ZQ Xu Advances in Neural Information Processing Systems 35, 26021-26033, 2022 | 18 | 2022 |
Towards understanding the condensation of neural networks at initial training H Zhou, Z Qixuan, T Luo, Y Zhang, ZQ Xu Advances in Neural Information Processing Systems 35, 2184-2196, 2022 | 18 | 2022 |
Dropout in training neural networks: Flatness of solution and noise structure Z Zhang, H Zhou, ZQJ Xu arXiv preprint arXiv:2111.01022, 2021 | 2 | 2021 |
Understanding the Initial Condensation of Convolutional Neural Networks Z Zhou, H Zhou, Y Li, ZQJ Xu arXiv preprint arXiv:2305.09947, 2023 | 1 | 2023 |