Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features

16 May 2024

Papers citing "Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features"

8 / 8 papers shown

Title
Towards the Three-Phase Dynamics of Generalization Power of a DNN Yuxuan He Junpeng Zhang Hongyuan Zhang Quanshi Zhang AI4CE 26 0 0 11 May 2025
Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey Yunkai Dang Kaichen Huang Jiahao Huo Yibo Yan S. Huang ... Kun Wang Yong Liu Jing Shao Hui Xiong Xuming Hu LRM 101 15 0 03 Dec 2024
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference Yuan Zhang Chun-Kai Fan Junpeng Ma Wenzhao Zheng Tao Huang ... Denis A. Gudovskiy Tomoyuki Okuno Yohei Nakata Kurt Keutzer Shanghang Zhang VLM 30 37 0 06 Oct 2024
Towards the Dynamics of a DNN Learning Symbolic Interactions Qihan Ren Yang Xu Junpeng Zhang Yue Xin Dongrui Liu Quanshi Zhang 26 7 0 27 Jul 2024
Explaining How a Neural Network Play the Go Game and Let People Learn Huilin Zhou Huijie Tang Mingjie Li Hao Zhang Zhenyu Liu Quanshi Zhang 33 6 0 15 Oct 2023
A Unified Game-Theoretic Interpretation of Adversarial Robustness Jie Ren Die Zhang Yisen Wang Lu Chen Zhanpeng Zhou ... Xu Cheng Xin Wang Meng Zhou Jie Shi Quanshi Zhang AAML 72 22 0 12 Mar 2021
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 284 2,890 0 15 Sep 2016
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 119 577 0 27 Feb 2015